© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79470
    Prev
    Next
    INDEX
    Explanations

    ну ла, ну ме, ну ка, ну жную

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    I
    1.49
    od
    1.19
    )
    1.13
    Z
    1.12
    ib
    1.09
    ్
    1.09
    و
    1.08
     lysates
    1.07
    ्यूस
    1.06
    ੀ
    1.05
    POSITIVE LOGITS
    к
    1.56
    ק
    1.56
    то
    1.54
     to
    1.50
    to
    1.49
    ется
    1.49
     on
    1.48
    ني
    1.37
    し
    1.33
    ing
    1.30
    Activations Density 0.000%

    No Known Activations