© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 36137
    Prev
    Next
    INDEX
    Explanations

    Pt reports / complains / ptotic

    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_7_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
    ↵
    0.37
     I
    0.25
     a
    0.23
     be
    0.23
    at
    0.22
     also
    0.20
    </h3>
    0.20
     L
    0.19
    i
    0.19
     zet
    0.19
    POSITIVE LOGITS
    ra
    0.26
    나
    0.25
    ในสนาม
    0.25
    د
    0.24
    ﾅ
    0.23
    手続き
    0.22
    
    0.22
    メリカ
    0.22
    𝟮
    0.22
    ೨
    0.22
    Activations Density 0.001%

    No Known Activations