© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3136
    Prev
    Next
    INDEX
    Explanations

    swift code

    oai_token-act-pair · gemini-2.0-flash

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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>
    -0.91
    WebVitals
    -0.55
    AndEndTag
    -0.52
    <em>
    -0.50
     mediu
    -0.48
    期刊论文
    -0.44
    classID
    -0.44
    Bibliograf
    -0.44
    ByPrimaryKey
    -0.44
    The
    -0.44
    POSITIVE LOGITS
    aarrggbb
    0.73
     numerus
    0.73
     Wiktionnaire
    0.73
    httphttps
    0.72
     виправивши
    0.69
     beginnetje
    0.68
     []).
    0.68
    PerformLayout
    0.68
    NameInMap
    0.66
    $_['
    0.63
    Activations Density 16.110%

    No Known Activations