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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260077
    Prev
    Next
    INDEX
    Explanations

    withdrawal and notice

    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
    J
    0.81
    th
    0.81
     equestrian
    0.77
    ch
    0.72
    v
    0.71
    Z
    0.71
     J
    0.70
     undersigned
    0.68
    E
    0.68
     ,
    0.67
    POSITIVE LOGITS
    Без
    1.11
    smallestBlock
    0.97
    ﭥ
    0.95
     parabol
    0.92
    -*
    0.92
    ដំណ
    0.90
    <unused80>
    0.88
    -【
    0.85
    Magnet
    0.84
     SrvGroup
    0.84
    Activations Density 0.000%

    No Known Activations