© 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. 167650
    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
     allongé
    0.40
     मसाला
    0.38
     adjusts
    0.36
     godiš
    0.35
     கூடுதல்
    0.34
    影
    0.34
    ബരിമല
    0.34
     दब
    0.34
     Multip
    0.34
    NSURL
    0.34
    POSITIVE LOGITS
    망
    0.38
     originating
    0.37
    Milwaukee
    0.37
    Provenance
    0.37
    >−</
    0.36
     }-\
    0.35
    பெரும்
    0.35
    这是一个
    0.35
    是一家
    0.35
     vast
    0.34
    Activations Density 0.000%

    No Known Activations