© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36297
    Prev
    Next
    INDEX
    Explanations

    audibility, Audacity, Audrey, Audhumla

    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
    </h3>
    0.71
    \
    0.71
     on
    0.70
     dejar
    0.70
    0.70
    ב
    0.67
    ри
    0.67
     freno
    0.67
    kowe
    0.66
    ι
    0.66
    POSITIVE LOGITS
    ਰ
    0.83
    car
    0.73
    Aud
    0.71
    iv
    0.68
    that
    0.68
    ੰਜ
    0.66
    camel
    0.64
    curve
    0.64
    ci
    0.63
    기준
    0.63
    Activations Density 0.017%

    No Known Activations