© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134338
    Prev
    Next
    INDEX
    Explanations

    lagarto, lagern, lagos

    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_1_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
    л
    1.52
    ма
    1.43
    ב
    1.33
    ED
    1.30
    м
    1.28
    мо
    1.26
    ста
    1.21
    AFTER
    1.21
    на
    1.19
    кой
    1.18
    POSITIVE LOGITS
    iv
    1.07
    um
    1.00
    ри
    0.99
    類型
    0.96
    ai
    0.95
    och
    0.95
     ilang
    0.95
     و
    0.91
    ação
    0.91
     lähe
    0.91
    Activations Density 0.000%

    No Known Activations