© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7331
    Prev
    Next
    INDEX
    Explanations

    */

    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
    ు
    2.87
    ಟಿ
    2.63
    ities
    2.63
    员
    2.48
    ில்
    2.45
     cirrh
    2.43
     dau
    2.37
     mingled
    2.36
    *>
    2.36
     Menge
    2.34
    POSITIVE LOGITS
    uterine
    2.79
    کی
    2.64
    ukuran
    2.60
    и
    2.58
    ма
    2.53
    ла
    2.42
    it
    2.38
    ness
    2.38
    gra
    2.36
    טת
    2.32
    Activations Density 0.003%

    No Known Activations