© 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-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175938
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    یدن
    0.52
    یده
    0.51
    وم
    0.45
    یدم
    0.44
    гиз
    0.42
     Planta
    0.41
     triangular
    0.41
    룹
    0.41
    рина
    0.40
    یدار
    0.40
    POSITIVE LOGITS
    void
    0.47
     aub
    0.45
     રાખો
    0.44
    шон
    0.44
    Orth
    0.43
    mani
    0.42
    ot
    0.41
    ioni
    0.41
    unati
    0.41
    hitting
    0.41
    Activations Density 0.003%

    No Known Activations