© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13528
    Prev
    Next
    INDEX
    Explanations

    instances of people or groups of people being referenced

    oai_token-act-pair · gemini-2.0-flash

    Text excerpts

    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
     who
    -3.55
    who
    -3.06
    Who
    -2.72
     Who
    -2.70
     quien
    -2.45
     whom
    -2.33
     quién
    -2.11
    whom
    -2.11
    WHO
    -2.02
     WHO
    -1.95
    POSITIVE LOGITS
     nahilalakip
    0.93
    SharedCtor
    0.72
     الاطلاع
    0.68
     utafiti
    0.68
    ArrowToggle
    0.67
     lenker
    0.66
    Ծանոթ
    0.63
     Réponses
    0.60
    writeFieldEnd
    0.60
    getMinutes
    0.60
    Activations Density 5.905%

    No Known Activations