© 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. 220326
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    1
    0.64
    4
    0.63
    Draw
    0.54
     Ε
    0.53
    Medical
    0.53
    <0x0D>
    0.52
    Glucose
    0.52
    Diabetes
    0.51
    melier
    0.51
    3
    0.51
    POSITIVE LOGITS
    的能力
    0.63
    ୍କ
    0.52
     വിൽപ്പന
    0.49
     décadas
    0.49
    ᄑ
    0.49
     ಗ್ರಾ
    0.49
     لمبے
    0.48
    ැනි
    0.48
     концер
    0.48
    ッフ
    0.47
    Activations Density 0.000%

    No Known Activations