© 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. 156298
    Prev
    Next
    INDEX
    Explanations

    raindrops

    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
    أ
    1.50
    一
    1.45
    /
    1.45
    y
    1.38
    The
    1.35
    是
    1.29
    .
    1.26
    of
    1.24
    ?
    1.24
    U
    1.23
    POSITIVE LOGITS
    ない
    1.66
    daki
    1.61
    ס
    1.54
    ться
    1.52
    ある
    1.49
    с
    1.46
    ل
    1.45
    لین
    1.41
    ൈ
    1.40
    на
    1.39
    Activations Density 0.001%

    No Known Activations