© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127026
    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_37_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
     zare
    0.41
    }||
    0.38
    ák
    0.38
     trich
    0.37
     Scot
    0.37
     Tutak
    0.36
     Trish
    0.36
    行
    0.36
    LEGO
    0.36
     Rash
    0.36
    POSITIVE LOGITS
     fördern
    0.41
     entfernen
    0.39
     Concern
    0.37
    Webpack
    0.36
     сани
    0.35
     मिठाई
    0.35
    眷
    0.35
    liquibase
    0.34
     संर
    0.34
     delineate
    0.34
    Activations Density 0.000%

    No Known Activations