© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6032
    Prev
    Next
    INDEX
    Explanations

    recent developments or additions

    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
    া
    2.91
    a
    2.86
    на
    2.84
    ⃙
    2.72
    ন
    2.50
    ா
    2.45
    од
    2.45
    ে
    2.41
    愪
    2.37
     jsonify
    2.33
    POSITIVE LOGITS
    pract
    2.84
    أة
    2.52
    ся
    2.42
     cedo
    2.39
    camb
    2.36
     urt
    2.30
    emplo
    2.29
     impetus
    2.25
     awhile
    2.19
     liber
    2.19
    Activations Density 0.065%

    No Known Activations