© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11980
    Prev
    Next
    INDEX
    Explanations

    speech, either by referring to people talking, using quotes, or by finding intensifiers

    oai_token-act-pair · gemini-2.0-flash

    Introductory words/phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     review
    -0.47
    amp
    -0.46
    出版年
    -0.44
    佑
    -0.44
    生
    -0.44
    aufen
    -0.44
     role
    -0.43
    Subclass
    -0.42
     pula
    -0.42
    den
    -0.42
    POSITIVE LOGITS
     ModelExpression
    0.87
     ExecuteAsync
    0.77
    TypedDataSet
    0.76
    WebVitals
    0.73
    发表于
    0.69
    Geplaatst
    0.68
     تضيفلها
    0.65
     HttpNotFound
    0.64
    ftagPool
    0.64
    sequelize
    0.63
    Activations Density 1.178%

    No Known Activations