© 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
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 260742
    Prev
    Next
    INDEX
    Explanations

    payment pending

    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
     Rach
    0.83
     شکل
    0.80
    래
    0.79
    urahan
    0.76
    Because
    0.72
     സമ്
    0.71
    чня
    0.71
    Experiment
    0.70
    $\$
    0.70
     десяти
    0.70
    POSITIVE LOGITS
     factions
    0.94
     sectarian
    0.91
     Declar
    0.89
     showbiz
    0.88
     অপে
    0.88
     Mafia
    0.88
    itiv
    0.88
     proclaiming
    0.88
    ilangkan
    0.88
     prerequisites
    0.87
    Activations Density 0.000%

    No Known Activations