© 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. 210616
    Prev
    Next
    INDEX
    Explanations

    opening a

    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
    br
    0.24
    region
    0.23
    ep
    0.22
    in
    0.20
    es
    0.20
    revolution
    0.20
    Device
    0.19
    Mechanism
    0.19
    g
    0.19
    kn
    0.19
    POSITIVE LOGITS
     are
    0.27
     Isl
    0.21
     archival
    0.21
     aperta
    0.20
    იდ
    0.19
     adaptable
    0.19
     similarities
    0.19
     ανο
    0.19
    ນ
    0.19
    𝗡
    0.19
    Activations Density 0.009%

    No Known Activations