© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198791
    Prev
    Next
    INDEX
    Explanations

    beard oil or balm

    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_12_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
    ;$
    0.30
    Rota
    0.30
    Vienna
    0.30
    Dj
    0.29
    Pho
    0.29
    джу
    0.29
    Hair
    0.29
    Bars
    0.29
    ;<
    0.29
    Gand
    0.29
    POSITIVE LOGITS
     quantitative
    0.30
     נ
    0.30
     drew
    0.29
     circulated
    0.29
     culp
    0.28
     것도
    0.28
     trustee
    0.28
     divisional
    0.28
     also
    0.28
    <0x98>
    0.28
    Activations Density 0.000%

    No Known Activations