© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37135
    Prev
    Next
    INDEX
    Explanations

    tsinghua University

    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
     Ecusson
    0.71
    والفقار
    0.68
    뗑
    0.66
     ligature
    0.63
    vykor
    0.63
    有所
    0.62
    <?=
    0.62
     তৃণ
    0.61
     लोकार्
    0.60
    ائیں
    0.59
    POSITIVE LOGITS
     a
    1.26
    I
    0.83
     an
    0.78
     be
    0.77
    é
    0.77
     s
    0.77
    li
    0.77
    ן
    0.74
    ts
    0.71
    ING
    0.71
    Activations Density 0.000%

    No Known Activations