© 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. 141456
    Prev
    Next
    INDEX
    Explanations

    zebra stripes

    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
    수인
    0.54
    }.
    0.50
    ").
    0.49
    Kost
    0.48
     WAS
    0.47
     HT
    0.46
    ო
    0.46
    HT
    0.46
    .}$
    0.46
    ').
    0.45
    POSITIVE LOGITS
    vação
    0.52
    stellar
    0.49
    ಸ್ತಕ
    0.49
    мий
    0.49
     funky
    0.48
    trag
    0.48
     champagne
    0.48
    had
    0.47
     સમા
    0.47
    có
    0.46
    Activations Density 0.002%

    No Known Activations