© 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. 34038
    Prev
    Next
    INDEX
    Explanations

    Jeff Beck, Robertson, Fitzgerald, whisky

    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
    ри
    0.80
    ной
    0.76
    twist
    0.73
    ли
    0.70
    ле
    0.70
    ні
    0.70
    т
    0.69
    виси
    0.68
    рат
    0.66
    directives
    0.66
    POSITIVE LOGITS
    ;
    0.77
     ito
    0.74
     REI
    0.73
     n
    0.72
     toh
    0.72
    ある
    0.69
     LO
    0.68
    การ
    0.68
     Ito
    0.66
     k
    0.65
    Activations Density 0.001%

    No Known Activations