© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49553
    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
    ოდ
    0.36
    ")}
    0.32
    PERTIES
    0.32
     $+\
    0.31
     INSTITUTE
    0.30
     لف
    0.30
     ""}
    0.30
    チャレンジ
    0.30
    IFICATE
    0.30
    锭
    0.30
    POSITIVE LOGITS
     descent
    0.38
     CME
    0.35
    sack
    0.35
     Granger
    0.34
     belt
    0.34
     Salomon
    0.33
     வெளியான
    0.32
     Gabriele
    0.32
     Han
    0.32
     Sab
    0.32
    Activations Density 0.000%

    No Known Activations