© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3016
    Prev
    Next
    INDEX
    Explanations

    descriptive or statistical words about a subject

    oai_token-act-pair · gemini-2.0-flash

    specific technical or programming terms

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

    current situations

    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
     become
    -2.48
     becoming
    -2.33
     Become
    -2.28
     becomes
    -2.23
    become
    -2.22
     became
    -2.16
     Becoming
    -2.14
    Becoming
    -2.09
    becoming
    -2.08
    Become
    -2.06
    POSITIVE LOGITS
     avoient
    0.48
     geométrico
    0.47
    FXML
    0.46
     beijo
    0.44
     is
    0.44
    alou
    0.43
    HideFlags
    0.41
     vainqueur
    0.41
    sidian
    0.40
     هستید
    0.40
    Activations Density 3.292%

    No Known Activations