© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180112
    Prev
    Next
    INDEX
    Explanations

    activities and concepts

    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_24_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
    뚤
    0.40
    睗
    0.38
     Charts
    0.38
    秙
    0.38
    㫧
    0.37
     descobrir
    0.37
     Textured
    0.36
     ficción
    0.36
    絭
    0.36
    畞
    0.35
    POSITIVE LOGITS
    like
    0.42
     pernicious
    0.40
    while
    0.39
    for
    0.39
    after
    0.38
     after
    0.36
    eron
    0.35
    A
    0.34
    ?!
    0.34
    prices
    0.34
    Activations Density 0.012%

    No Known Activations