© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6443
    Prev
    Next
    INDEX
    Explanations

    uses latex math symbols

    oai_token-act-pair · gemini-2.0-flash

    mathcal

    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
    <bos>
    -1.74
     myſelf
    -1.01
     Efq
    -0.96
     raiſ
    -0.95
     uſed
    -0.93
     Theſe
    -0.90
     ſtand
    -0.90
     auffi
    -0.90
     ainfi
    -0.89
     avoient
    -0.89
    POSITIVE LOGITS
    ,
    0.63
    <eos>
    0.57
     recently
    0.56
    <i>
    0.56
     good
    0.54
    <td>
    0.52
     (
    0.47
     various
    0.47
     recent
    0.46
     highly
    0.46
    Activations Density 0.983%

    No Known Activations