© 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. 1118
    Prev
    Next
    INDEX
    Explanations

    punctuation interspersed with words and/or numbers related to human emotion or personal narratives.

    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
     why
    -0.57
    mmung
    -0.56
     nobody
    -0.54
     what
    -0.52
    fır
    -0.51
     strange
    -0.51
    nobody
    -0.51
     lives
    -0.50
    strange
    -0.50
     Periodicals
    -0.50
    POSITIVE LOGITS
     oprot
    0.62
     nahilalakip
    0.55
     BoxDecoration
    0.55
     الحره
    0.54
     defaultstate
    0.54
    tagHelperRunner
    0.53
    AndEndTag
    0.53
     الاطلاع
    0.51
    bootstrapcdn
    0.50
    VersionUID
    0.50
    Activations Density 8.652%

    No Known Activations