© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16557
    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_34_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
    鹳
    0.43
    вёр
    0.38
    뜩
    0.38
     vuccanti
    0.37
     regularmente
    0.36
     জাদু
    0.35
    แหล่ง
    0.35
     TRADE
    0.34
     Blanch
    0.34
    whitespace
    0.34
    POSITIVE LOGITS
     gh
    0.38
     Djibouti
    0.37
    その他の
    0.37
     saving
    0.35
     সহযোগিতা
    0.35
     [{"
    0.35
    靱
    0.34
     https
    0.34
     Gh
    0.34
     Cheapest
    0.34
    Activations Density 0.000%

    No Known Activations