© 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. 136452
    Prev
    Next
    INDEX
    Explanations

    json/yaml structure

    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
    ka
    0.84
    p
    0.70
    ca
    0.66
    h
    0.66
    k
    0.64
    פ
    0.61
    br
    0.60
    ot
    0.60
    6
    0.58
    ba
    0.57
    POSITIVE LOGITS
    িন্দু
    0.62
     Matte
    0.58
     recou
    0.56
    sembled
    0.55
    鉭
    0.54
     autoimmune
    0.51
    ໃຈ
    0.51
     emotion
    0.50
    Terminal
    0.50
     عرصے
    0.50
    Activations Density 0.000%

    No Known Activations