© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81006
    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     einges
    0.44
     WAVE
    0.43
     waveguide
    0.42
     Wave
    0.40
     হাইড্র
    0.40
     Progn
    0.40
    adopted
    0.38
    ∏
    0.38
    raff
    0.38
     progn
    0.38
    POSITIVE LOGITS
     सख्ती
    0.38
    這一
    0.37
    scriptsize
    0.37
     облі
    0.37
    Prev
    0.36
     প্রাই
    0.36
    Prim
    0.36
    ೈಸ
    0.36
    Attractive
    0.35
    Comic
    0.35
    Activations Density 0.000%

    No Known Activations