© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27464
    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_40_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
     ríos
    0.40
    桷
    0.39
    ɕ
    0.38
    ogenicity
    0.38
    PROTON
    0.37
     fertility
    0.37
     Cata
    0.36
    ➝
    0.36
     ಕ್ಯಾ
    0.36
     Catania
    0.36
    POSITIVE LOGITS
    Kill
    0.47
    kill
    0.43
     Kill
    0.39
    Jh
    0.38
    Killing
    0.38
     زائد
    0.37
    JV
    0.37
     kill
    0.37
    物质
    0.37
     bons
    0.37
    Activations Density 0.002%

    No Known Activations