© 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. 139323
    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
    hrmacht
    0.42
     colonies
    0.38
    GMT
    0.38
     Gai
    0.37
    iotics
    0.37
     সোসাই
    0.37
    Ѕ
    0.36
    Kai
    0.36
     ương
    0.35
    ാത്ത
    0.35
    POSITIVE LOGITS
     கள
    0.39
    ருடன்
    0.38
    膏
    0.37
     আনার
    0.36
    ﺄ
    0.36
     repeated
    0.36
    羔
    0.36
     Leandro
    0.35
    ADDED
    0.35
    bath
    0.35
    Activations Density 0.000%

    No Known Activations