© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205280
    Prev
    Next
    INDEX
    Explanations

    guanine

    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_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     erstmals
    0.70
    árd
    0.67
    ension
    0.66
    п
    0.66
    <0x80>
    0.65
    માં
    0.65
     starten
    0.64
    ج
    0.63
    ación
    0.63
     immerse
    0.63
    POSITIVE LOGITS
    as
    0.88
     кора
    0.72
     COMPET
    0.71
    Ris
    0.71
    蚌
    0.69
    ccccn
    0.69
    with
    0.67
     Softball
    0.67
    Ком
    0.65
     Ants
    0.65
    Activations Density 0.001%

    No Known Activations