© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58276
    Prev
    Next
    INDEX
    Explanations

    dermal, epidermis, dermato

    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_2_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
    ς
    1.34
    <0x80>
    1.20
    0
    1.14
    ۰
    1.06
    ري
    1.04
    的选择
    1.04
    aría
    1.03
    的代码
    0.97
    ों
    0.96
     transmissão
    0.95
    POSITIVE LOGITS
     for
    1.54
    p
    1.25
    ص
    1.25
    an
    1.23
     to
    1.18
    ان
    1.16
    of
    1.10
    i
    1.09
    К
    1.06
    र
    1.04
    Activations Density 0.000%

    No Known Activations