© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60127
    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_11_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
    }$;
    0.67
     सब्जी
    0.63
     высокий
    0.63
     วิธี
    0.63
     karte
    0.62
     स्थिति
    0.61
     logistic
    0.61
    ábado
    0.60
     Centrum
    0.59
     लिए
    0.59
    POSITIVE LOGITS
    ان
    0.62
    ות
    0.62
    还
    0.62
    ત
    0.60
    عل
    0.58
    న
    0.58
    ય
    0.58
    ال
    0.57
    تش
    0.57
    ס
    0.57
    Activations Density 0.000%

    No Known Activations