© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13677
    Prev
    Next
    INDEX
    Explanations

    instances of emotional reactions or strong subjective feelings

    oai_token-act-pair · gemini-2.0-flash

    Intensifying adverbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Monfieur
    -0.63
     whoſe
    -0.62
     Urbano
    -0.58
    IsMutable
    -0.57
     ſche
    -0.57
     theſe
    -0.56
     Donc
    -0.55
     auffi
    -0.55
     ſeveral
    -0.55
     siè
    -0.54
    POSITIVE LOGITS
    PreferredItem
    0.69
    migrationBuilder
    0.67
    WithIOException
    0.65
    findpost
    0.60
    SPJ
    0.55
    SequentialGroup
    0.55
    WireFormatLite
    0.55
    المناصب
    0.53
    oves
    0.52
    InjectAttribute
    0.52
    Activations Density 1.425%

    No Known Activations