© 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. 5779
    Prev
    Next
    INDEX
    Explanations

    news headlines with colons, times, and URLs

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks

    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
     how
    -0.91
     what
    -0.75
     why
    -0.68
     “
    -0.62
     more
    -0.62
     new
    -0.62
    how
    -0.62
     autorytatywna
    -0.61
     muualla
    -0.60
     How
    -0.56
    POSITIVE LOGITS
    '
    1.04
    <bos>
    0.64
    '$
    0.59
    ’
    0.57
     оригіналу
    0.55
    issime
    0.55
     Arquivado
    0.55
    SupportActionBar
    0.53
     AssemblyCulture
    0.52
    קישורים
    0.52
    Activations Density 7.215%

    No Known Activations