© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51505
    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
    减
    0.43
    減
    0.42
     portanto
    0.40
    अनु
    0.39
    AYLOR
    0.37
     chc
    0.36
     subst
    0.36
     სწ
    0.36
     জঙ্গ
    0.35
     pertain
    0.35
    POSITIVE LOGITS
     syndrome
    0.39
     Elli
    0.34
     Syndrome
    0.34
    퀸
    0.34
    ernet
    0.33
     trồng
    0.33
     geopolitical
    0.33
    rightbar
    0.33
     hijacked
    0.33
     squads
    0.33
    Activations Density 0.000%

    No Known Activations