© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3006
    Prev
    Next
    INDEX
    Explanations

    new object creation

    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_5_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
    னர்
    1.97
     outfile
    1.93
    $-$
    1.90
    michael
    1.89
    ʍ
    1.84
    ESH
    1.79
    🗞
    1.79
    ❯
    1.78
    clothing
    1.75
    💭
    1.75
    POSITIVE LOGITS
     ð
    1.78
    그리고
    1.71
    ுங்கள்
    1.60
    ления
    1.50
    eli
    1.47
    ță
    1.46
     Nxh
    1.45
     Și
    1.45
    ̺
    1.44
     pravo
    1.43
    Activations Density 0.002%

    No Known Activations