© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206783
    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_10_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
    förm
    0.66
    fishing
    0.60
    burning
    0.58
    lf
    0.57
    t
    0.55
    sl
    0.54
    sv
    0.54
     Were
    0.52
     Replies
    0.52
    np
    0.52
    POSITIVE LOGITS
     previs
    0.57
     новый
    0.54
    ת
    0.54
     perdido
    0.54
     сможете
    0.51
     FODC
    0.50
     modestly
    0.50
     vidi
    0.50
     fallback
    0.49
    開始
    0.49
    Activations Density 0.000%

    No Known Activations