© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54719
    Prev
    Next
    INDEX
    Explanations

    **

    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_31_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
    bundled
    0.30
     સંદેશ
    0.27
    AlignedText
    0.27
    ْد
    0.27
    ستين
    0.27
    甴
    0.27
    KeyboardButton
    0.26
    AsString
    0.26
     simbolo
    0.26
    렴
    0.26
    POSITIVE LOGITS
    ...</
    0.29
    shr
    0.28
    ...",
    0.28
     doctr
    0.27
     THR
    0.27
     cake
    0.27
     действительно
    0.27
    cake
    0.27
     settles
    0.27
     bale
    0.26
    Activations Density 0.015%

    No Known Activations