© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3822
    Prev
    Next
    INDEX
    Explanations

    the word "for," some uses of "if", action words related to the self, and a few common words like "that" and "to" possibly used contextually with the other words

    oai_token-act-pair · gemini-2.0-flash

    programming terms and code snippets

    np_token-act-pair-logits · gpt-4o-mini

    conversational directives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -0.57
     što
    -0.46
    cean
    -0.43
    omány
    -0.43
     hưởng
    -0.42
    mens
    -0.42
     équi
    -0.42
     Glaubens
    -0.42
     secondary
    -0.40
     Verte
    -0.40
    POSITIVE LOGITS
    UserScript
    0.69
     yourself
    0.69
    yourself
    0.68
    AndEndTag
    0.68
    ApiModelProperty
    0.67
    GEBURTSDATUM
    0.67
     виправивши
    0.65
     AppCompatTheme
    0.65
    featureID
    0.65
    RepeatedField
    0.63
    Activations Density 11.202%

    No Known Activations