© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123345
    Prev
    Next
    INDEX
    Explanations

    GPT, ALL, gay, Yeager, Dow, Witte

    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_3_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
    s
    0.93
    ت
    0.90
     on
    0.65
    ein
    0.65
    ের
    0.64
    }*/
    0.64
    తో
    0.63
    e
    0.62
    an
    0.61
    eau
    0.61
    POSITIVE LOGITS
    ri
    0.77
    se
    0.73
    ना
    0.72
    کس
    0.70
    ta
    0.65
     руководство
    0.65
    ους
    0.65
     CERN
    0.65
    ремя
    0.65
    ter
    0.64
    Activations Density 0.002%

    No Known Activations