© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24294
    Prev
    Next
    INDEX
    Explanations

    paths:

    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
    Not in Any Lists

    No Comments

    Negative Logits
     on
    0.75
    стью
    0.73
    b
    0.72
    ной
    0.68
     android
    0.64
    uña
    0.61
    D
    0.61
     nouă
    0.61
     be
    0.60
     was
    0.60
    POSITIVE LOGITS
    0.70
     mAbs
    0.68
     requisito
    0.61
     COMPOUNDS
    0.59
     modulating
    0.59
    ّر
    0.59
    ˒
    0.59
     tomto
    0.59
     многих
    0.58
     праз
    0.58
    Activations Density 0.003%

    No Known Activations