© 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. 162
    Prev
    Next
    INDEX
    Explanations

    words related to scientific research contexts, especially those associated with data analysis and interpretation of experiments

    oai_token-act-pair · gemini-2.0-flash

    Scientific research contexts

    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
     field
    -2.77
     Field
    -2.63
    Field
    -2.48
     FIELD
    -2.39
     fields
    -2.36
    field
    -2.31
     Fields
    -2.30
    FIELD
    -2.16
    Fields
    -2.09
    fields
    -2.05
    POSITIVE LOGITS
    CodeDom
    0.63
     по
    0.63
     wireType
    0.58
     cherchés
    0.57
     fi
    0.55
    jsxFileName
    0.55
    posób
    0.55
    OCCURRED
    0.53
    PreExecute
    0.52
    yntaxException
    0.52
    Activations Density 2.029%

    No Known Activations