© 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. 9587
    Prev
    Next
    INDEX
    Explanations

    the end of long lines consisting of underscores, and also the word "Explanation," and email addresses

    oai_token-act-pair · gemini-2.0-flash

    Underscores and explanation

    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
     photolibrary
    -1.05
    .³
    -1.01
     Efq
    -0.94
     Anſ
    -0.93
     Monfieur
    -0.91
     Shakspeare
    -0.90
     Jefus
    -0.90
     itſelf
    -0.90
    ArgsConstructor
    -0.89
     (\<
    -0.88
    POSITIVE LOGITS
    <bos>
    0.88
    '
    0.71
     in
    0.71
    <eos>
    0.68
     a
    0.68
    LookAnd
    0.67
     and
    0.65
    InitStruct
    0.62
    "
    0.60
    ma
    0.59
    Activations Density 0.686%

    No Known Activations