© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103101
    Prev
    Next
    INDEX
    Explanations

    Apple ID

    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_1_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
    ರ
    1.24
    ー
    1.14
    ן
    1.10
    ۰
    1.10
    ル
    1.06
    𝗹
    1.00
    ری
    0.98
    ۳
    0.96
    ຯ
    0.96
     multitudes
    0.95
    POSITIVE LOGITS
    on
    1.11
    1.03
    1.02
    O
    0.97
    ance
    0.89
    </b>
    0.87
    an
    0.87
    U
    0.86
    os
    0.85
    ak
    0.84
    Activations Density 0.001%

    No Known Activations