© 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. 54109
    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
    нений
    0.46
    ák
    0.41
    𝒗
    0.41
    rás
    0.40
    altro
    0.40
    ethylamine
    0.40
    autre
    0.39
    絣
    0.39
     profonde
    0.38
     ವಿಧಾನಸಭಾ
    0.38
    POSITIVE LOGITS
    
    0.37
     WOW
    0.36
     wow
    0.34
    ড্রিম
    0.34
    াপতি
    0.34
     victimization
    0.34
    InstanceOf
    0.33
    hydes
    0.33
    LLI
    0.33
     butchers
    0.33
    Activations Density 0.000%

    No Known Activations