© 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. 1646
    Prev
    Next
    INDEX
    Explanations

    nouns that could be titles of things like movies, books, studies, organizations, businesses, projects, etc

    oai_token-act-pair · 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
    versaire
    -0.59
     fotográfico
    -0.58
    edance
    -0.57
     magnético
    -0.57
     getChild
    -0.56
    cyklopedia
    -0.54
    ]--;
    -0.54
     argint
    -0.54
     plagioclase
    -0.53
    getGame
    -0.53
    POSITIVE LOGITS
    <bos>
    0.61
    -------
    0.52
    //
    0.51
    SourceChecksum
    0.51
    TestingModule
    0.49
    VersionUID
    0.47
    ArgsConstructor
    0.46
    Билгалдахарш
    0.46
     kaynağından
    0.45
    下载附件
    0.44
    Activations Density 0.528%

    No Known Activations