© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213683
    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_47_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
     hoist
    0.36
     broch
    0.35
    猥
    0.35
    FORE
    0.35
    확
    0.35
     ঘোষণা
    0.35
     来
    0.34
    ֛
    0.34
     ক্যারি
    0.34
     ठिका
    0.34
    POSITIVE LOGITS
    PPPP
    0.42
    푞
    0.40
     Relevance
    0.39
    बीआई
    0.38
    omus
    0.38
     Tempt
    0.38
    Qt
    0.38
    ENCES
    0.38
    িণ
    0.36
    QB
    0.35
    Activations Density 0.000%

    No Known Activations