© 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. 91424
    Prev
    Next
    INDEX
    Explanations

    reactively / APP_

    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
    MS
    0.77
    し
    0.71
    BS
    0.70
    SCI
    0.70
    adays
    0.66
    ST
    0.65
    PTO
    0.64
    Products
    0.64
    0.63
    ся
    0.63
    POSITIVE LOGITS
    n
    0.82
    ن
    0.71
    ic
    0.64
    க்
    0.64
    naz
    0.64
     realista
    0.64
    ي
    0.63
    na
    0.62
    s
    0.61
    nj
    0.58
    Activations Density 0.001%

    No Known Activations