© 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. 12160
    Prev
    Next
    INDEX
    Explanations

    Russian language fragments related to programming

    oai_token-act-pair · gemini-2.0-flash

    Mixed languages and code

    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
    ünstler
    -0.49
     чтения
    -0.49
    GetX
    -0.48
     сериала
    -0.47
     века
    -0.47
    ництва
    -0.46
    sui
    -0.46
     образования
    -0.46
    зова
    -0.46
    :]:
    -0.46
    POSITIVE LOGITS
    StoryboardSegue
    0.68
    posedge
    0.66
    存于互联网档案馆
    0.62
    endwhile
    0.62
    QMetaType
    0.61
    LookAnd
    0.61
    useNewUrlParser
    0.61
    ProgressHUD
    0.60
    setVerticalGroup
    0.57
    providedIn
    0.56
    Activations Density 0.423%

    No Known Activations