© 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. 140737
    Prev
    Next
    INDEX
    Explanations

    npm create start init

    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
     windy
    0.52
    W
    0.50
     exclusivos
    0.49
    H
    0.47
    ىم
    0.47
     prova
    0.46
     shady
    0.46
     soggy
    0.46
     lucrative
    0.45
     Informat
    0.45
    POSITIVE LOGITS
    üsseldorf
    0.59
    s
    0.57
    sé
    0.56
     세
    0.55
    세
    0.52
    log
    0.52
    se
    0.51
    las
    0.51
    six
    0.49
    logger
    0.48
    Activations Density 0.000%

    No Known Activations