© 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. 9408
    Prev
    Next
    INDEX
    Explanations

    the word "nothing" or "none" followed by an adjective

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "nothing"

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

    nothing

    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
     defaultstate
    -1.02
    RefNanny
    -0.91
    RenderAtEndOf
    -0.84
    quelize
    -0.81
    IntoConstraints
    -0.80
    Datuak
    -0.80
    AnchorStyles
    -0.79
     ModelExpression
    -0.77
     виправивши
    -0.75
    MigrationBuilder
    -0.73
    POSITIVE LOGITS
     particularly
    0.53
     more
    0.48
     particularmente
    0.47
     remarquable
    0.46
     particuli
    0.44
     occurring
    0.44
     occurred
    0.44
     špat
    0.43
     doulou
    0.43
     serious
    0.43
    Activations Density 1.228%

    No Known Activations