© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 363
    Prev
    Next
    INDEX
    Explanations

    various math symbols and equation components within mathematical or scientific text

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ModelExpression
    -0.66
     relève
    -0.56
     ISNI
    -0.54
    Demografía
    -0.53
    EndGlobalSection
    -0.52
     ProtoMessage
    -0.52
     externi
    -0.50
     Puget
    -0.49
    tangentMode
    -0.49
    cloudflare
    -0.47
    POSITIVE LOGITS
     Opinion
    0.59
     doInBackground
    0.57
     typelib
    0.57
    bootstrapcdn
    0.56
    帖最后由
    0.55
    principalTable
    0.54
    IntoConstraints
    0.54
    OCCURRED
    0.54
    IBOutlet
    0.52
     IBOutlet
    0.49
    Activations Density 3.458%

    No Known Activations