© 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. 46655
    Prev
    Next
    INDEX
    Explanations

    New Century, New Look, New Words, New Moon, New People, New Revised, New Magazine

    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
    kker
    0.61
    dens
    0.57
    dte
    0.55
    dem
    0.55
    噰
    0.55
    كة
    0.54
    daki
    0.54
    ließlich
    0.53
    dienst
    0.52
    ккей
    0.52
    POSITIVE LOGITS
     to
    1.02
    지
    0.86
    ur
    0.85
    로
    0.83
    is
    0.73
    ای
    0.71
    ون
    0.69
     that
    0.68
    ین
    0.67
    জ
    0.66
    Activations Density 0.009%

    No Known Activations