© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194354
    Prev
    Next
    INDEX
    Explanations

    cashback

    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_4_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
    en
    1.10
    oster
    0.93
    ?
    0.91
    er
    0.86
    ed
    0.84
    ie
    0.82
    is
    0.81
    imizu
    0.78
    et
    0.74
    ind
    0.73
    POSITIVE LOGITS
    คุณ
    0.90
    เรา
    0.90
    the
    0.89
    ك
    0.77
    g
    0.77
    ﺔ
    0.75
    ק
    0.74
    ﻪ
    0.74
    پ
    0.73
    กับ
    0.72
    Activations Density 0.000%

    No Known Activations