© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 7985
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially pertaining to HTML or numerical/statistical data

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.71
    ung
    -0.38
    u
    -0.33
     "'",
    -0.33
    ans
    -0.32
    lin
    -0.32
    l
    -0.30
    ».
    -0.30
     allAfrica
    -0.30
     onData
    -0.30
    POSITIVE LOGITS
     Efq
    0.65
     Monfieur
    0.59
     Majefty
    0.58
     Theſe
    0.56
     purpoſe
    0.56
     pleaſure
    0.55
     كومونز
    0.55
     ſeveral
    0.55
     Jefus
    0.54
     Chriftian
    0.52
    Activations Density 0.958%

    No Known Activations