© 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. 5868
    Prev
    Next
    INDEX
    Explanations

    self-deprecating

    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
    ا
    1.10
    र्गत
    0.98
    orsement
    0.97
    ύτε
    0.97
     veritable
    0.97
    stuffs
    0.96
    avigation
    0.95
     lawn
    0.95
     tõ
    0.95
    ازه
    0.95
    POSITIVE LOGITS
     byteArray
    1.04
     следующие
    1.03
     administ
    1.00
     наличие
    0.97
    Очень
    0.95
    О
    0.94
     sightings
    0.92
    ℍ
    0.90
     isto
    0.88
    و
    0.88
    Activations Density 0.002%

    No Known Activations