© 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. 58242
    Prev
    Next
    INDEX
    Explanations

    expression of smiling

    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
    та
    1.41
    ка
    1.20
    ;
    1.17
    و
    1.08
    ना
    1.07
    ק
    1.05
    ную
    1.04
    вь
    1.04
    פ
    1.02
    нов
    1.02
    POSITIVE LOGITS
    U
    1.38
    L
    1.30
    N
    1.20
    J
    1.13
    il
    1.11
    W
    1.10
    X
    1.10
     or
    1.09
    T
    1.06
    S
    1.05
    Activations Density 0.001%

    No Known Activations