© 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. 140922
    Prev
    Next
    INDEX
    Explanations

    lipoma dissolution

    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
    I
    0.21
    C
    0.19
    <
    0.18
    $.
    0.17
    Huawei
    0.17
    love
    0.16
    sa
    0.16
    liw
    0.16
    %.
    0.16
    test
    0.16
    POSITIVE LOGITS
    }`}
    0.16
     MILLER
    0.15
     incentiv
    0.15
     negated
    0.14
     emphatic
    0.14
     subspaces
    0.14
     ""}
    0.14
     shuffling
    0.14
    ਾ
    0.14
     Doyle
    0.14
    Activations Density 0.001%

    No Known Activations