© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30270
    Prev
    Next
    INDEX
    Explanations

    tear or tearing

    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_10_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
    <0x80>
    0.22
    nels
    0.15
    barrow
    0.15
     кино
    0.14
    のかな
    0.14
     innovación
    0.14
     डिट
    0.14
    <0xBE>
    0.13
    forced
    0.13
     cinemas
    0.13
    POSITIVE LOGITS
    л
    0.17
     U
    0.17
    dU
    0.16
    d
    0.16
    ש
    0.16
    ס
    0.16
    <b>
    0.16
    .
    0.16
    ു
    0.16
     crowns
    0.15
    Activations Density 0.009%

    No Known Activations