© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12871
    Prev
    Next
    INDEX
    Explanations

    instances of someone waiting for something and considering options

    oai_token-act-pair · gemini-2.0-flash

    wait

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     peccato
    -0.54
    chene
    -0.50
    qrst
    -0.49
    AddHtmlAttribute
    -0.49
    сли
    -0.48
    yesi
    -0.47
    memberof
    -0.47
    vivi
    -0.46
    AddWithValue
    -0.45
    urilor
    -0.45
    POSITIVE LOGITS
    SharedCtor
    0.69
    InjectAttribute
    0.67
     ویکی‌پدیا
    0.65
    AutoScale
    0.64
    migrationBuilder
    0.63
    PyExc
    0.63
    SequentialGroup
    0.60
    MockMvc
    0.57
    EXPECT
    0.57
     Infórmanos
    0.57
    Activations Density 0.343%

    No Known Activations