© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156463
    Prev
    Next
    INDEX
    Explanations

    R sounds

    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_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    는
    1.05
    어
    1.05
    ون
    1.02
    是
    0.96
    大
    0.95
    ה
    0.95
    я
    0.95
    两
    0.95
    պ
    0.94
    は
    0.92
    POSITIVE LOGITS
    er
    1.13
    ر
    0.96
     I
    0.92
    ad
    0.91
     salted
    0.73
    ar
    0.73
    r
    0.72
    ,
    0.71
    eram
    0.70
    z
    0.70
    Activations Density 0.005%

    No Known Activations