© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 475
    Prev
    Next
    INDEX
    Explanations

    words related to fantasy books, Amazon products, and descriptors of coffee

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     kaarangay
    -1.11
    LookAnd
    -0.93
    EDEFAULT
    -0.92
    MigrationBuilder
    -0.92
    Cyfeiriadau
    -0.92
    ьаж
    -0.91
    Билгалдахарш
    -0.90
    ThroughAttribute
    -0.90
     Roskov
    -0.90
    ///</
    -0.88
    POSITIVE LOGITS
    de
    0.43
    na
    0.40
    hack
    0.40
    I
    0.38
     I
    0.38
    do
    0.37
    مكن
    0.37
    k
    0.37
    最快更新
    0.36
    <eos>
    0.35
    Activations Density 0.988%

    No Known Activations