© 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. 45696
    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
    чен
    0.47
    Desen
    0.46
    笏
    0.44
    privileged
    0.44
     precinct
    0.44
    čen
    0.43
    ิก
    0.43
    oggetto
    0.43
    сом
    0.42
    čené
    0.42
    POSITIVE LOGITS
     Lightfoot
    0.48
     இல
    0.46
    ⠊
    0.46
    iiii
    0.46
     drifts
    0.45
    インチ
    0.45
    栤
    0.45
     Ling
    0.45
    drift
    0.44
     ఇ
    0.44
    Activations Density 0.000%

    No Known Activations