© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158083
    Prev
    Next
    INDEX
    Explanations

    currant jelly

    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_2_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
    '
    1.52
    :
    1.14
    м
    1.13
     intentos
    1.05
    ą
    1.05
     имена
    1.05
    یر
    1.04
     vínculos
    1.02
    ী
    1.02
     eigenfunctions
    0.98
    POSITIVE LOGITS
    al
    1.62
    us
    1.33
    b
    1.28
    ed
    1.20
    ad
    1.09
    il
    1.06
    ee
    1.05
    ur
    1.04
    ang
    1.02
    ar
    0.95
    Activations Density 0.000%

    No Known Activations