© 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. 5995
    Prev
    Next
    INDEX
    Explanations

    emoticon :D or :3

    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
    o
    1.12
     doom
    0.98
    falls
    0.98
    ه
    0.97
    ী
    0.94
     sparsity
    0.94
     stint
    0.94
     protruding
    0.92
     venus
    0.91
    ほしい
    0.91
    POSITIVE LOGITS
    ेंगे
    0.94
    близи
    0.93
    overline
    0.93
     گا
    0.93
    ⎞
    0.91
    ਤਾ
    0.91
    =\{\
    0.90
    er
    0.90
     kijken
    0.90
    ,}$
    0.88
    Activations Density 0.002%

    No Known Activations