© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127158
    Prev
    Next
    INDEX
    Explanations

    oyster sauce, Ave, larvae

    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_3_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
    ’
    0.75
    kannya
    0.73
    ing
    0.71
    k
    0.67
    esting
    0.66
    kiego
    0.64
    kens
    0.64
    kans
    0.64
    า
    0.64
    alls
    0.63
    POSITIVE LOGITS
    t
    1.04
    r
    0.96
    වල
    0.71
    W
    0.71
    F
    0.68
    N
    0.66
    }";
    0.65
    G
    0.65
    يسي
    0.64
    D
    0.64
    Activations Density 0.000%

    No Known Activations