© 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. 34276
    Prev
    Next
    INDEX
    Explanations

    shawshank, shawarma, schattenruh

    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
    '
    0.86
    {
    0.66
    aris
    0.63
     ziel
    0.63
    ası
    0.62
    .
    0.62
     тема
    0.61
     ем
    0.61
     rey
    0.60
    arse
    0.59
    POSITIVE LOGITS
    ী
    0.89
    साठी
    0.70
    お
    0.70
    きたい
    0.66
    ש
    0.65
    ですが
    0.64
    ಷ್ಟು
    0.63
    ながら
    0.62
    دیا
    0.62
    다른
    0.62
    Activations Density 0.011%

    No Known Activations