© 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. 220369
    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
     দীননাথ
    0.43
    孛
    0.41
    讐
    0.38
    ’.
    0.38
    “.
    0.38
    نجليزية
    0.38
    汨
    0.38
    🌫
    0.38
     intellig
    0.37
    怖い
    0.36
    POSITIVE LOGITS
     parking
    0.47
     Parking
    0.41
     friction
    0.40
    Parking
    0.40
    parking
    0.40
     tensions
    0.38
    kick
    0.37
     perk
    0.37
    ingham
    0.37
     acclaim
    0.36
    Activations Density 0.000%

    No Known Activations