© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5174
    Prev
    Next
    INDEX
    Explanations

    code state updates

    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_3_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
    at
    2.57
    an
    2.13
    as
    1.96
    of
    1.90
    ad
    1.89
    া
    1.73
    ত
    1.70
    on
    1.67
    মিক্যাল
    1.63
    am
    1.63
    POSITIVE LOGITS
    $
    2.28
     počet
    2.15
    𝓷
    2.02
    
    2.00
    ${
    1.96
     говорить
    1.89
    }];
    1.86
     $('
    1.77
    $('
    1.75
    Ⴖ
    1.74
    Activations Density 0.005%

    No Known Activations