© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61053
    Prev
    Next
    INDEX
    Explanations

    q followed by punctuation or letters

    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_11_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
    ді
    0.75
    "]},
    0.61
     t
    0.61
     త
    0.61
     ]),
    0.61
    各地
    0.60
     parton
    0.59
     OF
    0.58
     ”,
    0.58
    둴
    0.58
    POSITIVE LOGITS
    uvo
    0.53
    into
    0.52
    fromParams
    0.52
    Inicio
    0.50
    ﺭ
    0.49
     permettant
    0.49
    bamos
    0.49
    Into
    0.48
    la
    0.48
    ValArr
    0.48
    Activations Density 0.001%

    No Known Activations