© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12433
    Prev
    Next
    INDEX
    Explanations

    the word "pad", and possibly related words like "strip"

    oai_token-act-pair · gemini-2.0-flash

    pad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     flamengo
    -0.70
     Gegenteil
    -0.70
     Reſ
    -0.67
     greateſt
    -0.65
     Chriftian
    -0.63
     fusca
    -0.62
    IndentedString
    -0.60
     Inſ
    -0.60
     Púb
    -0.60
     bogotá
    -0.59
    POSITIVE LOGITS
    AndEndTag
    0.78
    Autoritní
    0.76
    Xna
    0.76
     cherchés
    0.74
    +#+
    0.74
    FunctionFlags
    0.69
    MLLoader
    0.69
     nahilalakip
    0.68
     صوتيه
    0.68
    OGND
    0.66
    Activations Density 1.100%

    No Known Activations