© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198400
    Prev
    Next
    INDEX
    Explanations

    (NG+) Runs

    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_15_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
    ң
    0.14
     බ
    0.14
    ibilities
    0.13
    зиру
    0.13
    湿度
    0.13
    支付
    0.12
     discounts
    0.12
     समर्पण
    0.12
    ത്
    0.12
    \%
    0.12
    POSITIVE LOGITS
     inflater
    0.14
     cervello
    0.13
    reement
    0.13
    ("@
    0.13
    DELTA
    0.12
     نحاول
    0.12
     confirmer
    0.12
     neuronal
    0.12
     Todas
    0.12
     allora
    0.12
    Activations Density 0.002%

    No Known Activations