© 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. 12919
    Prev
    Next
    INDEX
    Explanations

    the word 'documentation', and possibly other words related to technical documentation

    oai_token-act-pair · gemini-2.0-flash

    documentation

    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
     heresy
    -0.66
     drago
    -0.63
    ulaski
    -0.63
     Bucs
    -0.63
     Mahomet
    -0.62
     SCE
    -0.62
     renunciation
    -0.62
     Moslem
    -0.61
     Merle
    -0.61
     Negroes
    -0.60
    POSITIVE LOGITS
     the
    0.86
     an
    0.71
    jsii
    0.69
     pinulongan
    0.69
    rungsseite
    0.68
     propOrder
    0.66
    addGap
    0.63
    gnancy
    0.60
    原始内容存档于
    0.60
    aarrggbb
    0.60
    Activations Density 1.159%

    No Known Activations