© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260381
    Prev
    Next
    INDEX
    Explanations

    doing better

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     too
    0.60
     br
    0.57
    resources
    0.55
    cover
    0.55
    T
    0.55
     cover
    0.53
     resources
    0.52
    gang
    0.52
     materials
    0.52
    ources
    0.51
    POSITIVE LOGITS
    𒉡
    0.60
     beatae
    0.59
     रहेको
    0.59
    <unused2145>
    0.58
     Amended
    0.58
     különböz
    0.57
     eius
    0.57
    <unused917>
    0.57
    >)`](
    0.56
    <unused737>
    0.55
    Activations Density 0.001%

    No Known Activations