© 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. 12252
    Prev
    Next
    INDEX
    Explanations

    the word "to" and words immediately following it.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    DoubleQuotes
    -0.69
    msgTypes
    -0.60
    ++){
    -0.60
     للاسماء
    -0.58
    '):
    -0.58
    parsedMessage
    -0.57
    oplasty
    -0.57
     BM
    -0.56
    깥
    -0.56
    sidian
    -0.55
    POSITIVE LOGITS
    eded
    0.50
    tierte
    0.44
    blooded
    0.43
    able
    0.43
    que
    0.42
     opportunity
    0.42
     tend
    0.41
     virgen
    0.41
    GraphicsUnit
    0.41
    LUT
    0.41
    Activations Density 6.186%

    No Known Activations