© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1375
    Prev
    Next
    INDEX
    Explanations

    the punctuation and conversational markers of quoted speech

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     working
    -0.75
     ExecuteAsync
    -0.70
    working
    -0.68
     leveraging
    -0.68
     oprot
    -0.67
     preserving
    -0.63
     elevating
    -0.62
     maintaining
    -0.61
     having
    -0.60
     prioritizing
    -0.60
    POSITIVE LOGITS
    InvalidProtocol
    0.54
    UserScript
    0.51
    not
    0.49
     saith
    0.47
    multer
    0.46
    Not
    0.46
    what
    0.44
    why
    0.44
    so
    0.44
     dollar
    0.44
    Activations Density 4.200%

    No Known Activations