© 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. 31439
    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
    操
    0.38
     effortlessly
    0.38
     отве
    0.36
    fores
    0.36
    ées
    0.36
     countably
    0.35
    Cyt
    0.34
     réponse
    0.34
     MySQL
    0.34
     effortless
    0.33
    POSITIVE LOGITS
    璞
    0.36
    芯片
    0.35
     Tribun
    0.35
    Casey
    0.35
    গে
    0.35
    পদার্থ
    0.35
     mView
    0.35
     adjour
    0.34
     Examining
    0.33
    
    0.33
    Activations Density 0.000%

    No Known Activations