Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 260713
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coerced
    1.23
    യിരുന്നു
    1.21
    летнего
    1.19
     sounded
    1.16
    Philippines
    1.16
    Excluded
    1.14
    <unused302>
    1.13
    modified
    1.09
    <unused127>
    1.08
    LECT
    1.08
    POSITIVE LOGITS
     atau
    1.14
    ியோ
    1.13
     sik
    1.11
     것이
    1.10
    ia
    1.08
     أو
    1.05
     belieb
    1.03
     یا
    1.03
    ជាក់
    1.03
     eller
    1.03
    Activations Density 0.000%

    No Known Activations