© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 885
    Prev
    Next
    INDEX
    Explanations

    references to history, geography, government, and statistics.

    oai_token-act-pair · gemini-2.0-flash

    United States

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    kloped
    -0.68
     lượt
    -0.58
    ArgsConstructor
    -0.58
     lenker
    -0.56
     يتيمه
    -0.54
    SequentialGroup
    -0.54
    providedIn
    -0.50
    PhysRev
    -0.50
    Referències
    -0.49
    UnsafeEnabled
    -0.49
    POSITIVE LOGITS
     us
    2.25
     u
    1.65
    us
    1.41
    u
    1.38
     united
    1.38
     Us
    1.16
    Us
    1.04
     ua
    1.02
    united
    0.99
     нас
    0.88
    Activations Density 17.541%

    No Known Activations