© 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. 49003
    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
    াদান
    0.41
    tStart
    0.40
    asets
    0.38
     ጥ
    0.38
    jsce
    0.37
    FJ
    0.37
    oreg
    0.37
    ច្
    0.35
    agni
    0.35
    tand
    0.35
    POSITIVE LOGITS
     COVID
    0.46
    疫情
    0.42
    馨
    0.41
     RMSE
    0.40
     कॉरिडोर
    0.39
     Heavy
    0.38
     Severity
    0.37
    消
    0.37
     живота
    0.36
     Inquiry
    0.36
    Activations Density 0.000%

    No Known Activations