© 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. 11752
    Prev
    Next
    INDEX
    Explanations

    words connecting ideas in academic writing, such as "central", "focus", "lens", and words to indicate future events.

    oai_token-act-pair · gemini-2.0-flash

    Academic/Analytical writing

    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
    ValueStyle
    -0.76
    principalTable
    -0.74
    UnusedPrivate
    -0.70
    "){
    -0.69
    المناصب
    -0.69
     للاسماء
    -0.69
     Мексичка
    -0.68
     utafitiHapana
    -0.67
    Autoritní
    -0.65
    énario
    -0.65
    POSITIVE LOGITS
     fix
    0.48
    insic
    0.44
    zid
    0.42
    bular
    0.42
    \!
    0.41
    лог
    0.40
    щика
    0.40
    plaid
    0.40
     Fix
    0.40
     làng
    0.40
    Activations Density 0.419%

    No Known Activations