© 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. 166939
    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
     دنی
    0.39
     prizes
    0.38
    otrans
    0.38
     किस्
    0.38
    관
    0.37
    Corpor
    0.36
    alach
    0.36
    laz
    0.35
    සුව
    0.35
    ग्राउंड
    0.35
    POSITIVE LOGITS
    暦
    0.41
     doubl
    0.39
     Inference
    0.38
     Suppression
    0.37
    འི་
    0.37
     dav
    0.36
    фикация
    0.36
     передви
    0.36
     Moves
    0.36
     bool
    0.35
    Activations Density 0.000%

    No Known Activations