© 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. 220404
    Prev
    Next
    INDEX
    Explanations

    convolutions, existence, absence

    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
     veineux
    0.30
     ис
    0.29
    ی
    0.29
     ischemic
    0.29
    м
    0.29
     humains
    0.28
    ມັນ
    0.27
     inhabiting
    0.27
    𝑠
    0.26
     אם
    0.26
    POSITIVE LOGITS
    ot
    0.36
    I
    0.29
    ，
    0.28
    Z
    0.28
    O
    0.27
    ik
    0.27
    J
    0.27
    un
    0.26
    4
    0.26
    et
    0.26
    Activations Density 0.011%

    No Known Activations