© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143197
    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_46_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
     D
    0.45
    𝐷
    0.43
     Д
    0.43
    കർ
    0.43
     डी
    0.40
     Alfonso
    0.40
    きる
    0.40
     الد
    0.39
    নাথ
    0.39
    躏
    0.39
    POSITIVE LOGITS
     multist
    0.40
    tre
    0.40
    chess
    0.39
    pit
    0.39
     valor
    0.38
     முன்னே
    0.37
    torch
    0.37
     solar
    0.37
     vaccine
    0.37
     assignment
    0.37
    Activations Density 0.000%

    No Known Activations