© 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. 220904
    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
     sinais
    0.41
    Rotating
    0.39
    ევე
    0.39
    భ
    0.39
    Terminology
    0.39
    首先
    0.38
    нак
    0.38
     首先
    0.37
    \|\
    0.37
     ಸಾಮಾನ್ಯವಾಗಿ
    0.36
    POSITIVE LOGITS
     user
    0.39
     cia
    0.38
    gwin
    0.38
     eagerness
    0.37
    掣
    0.37
     RESPECT
    0.37
     hob
    0.36
    vering
    0.36
     constricted
    0.36
     coffers
    0.36
    Activations Density 0.000%

    No Known Activations