© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236156
    Prev
    Next
    INDEX
    Explanations

    excellent, satisfactory, well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_32_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
    лями
    0.34
     unsupervised
    0.34
     eventually
    0.34
     chu
    0.33
     Eventually
    0.33
    <unused64>
    0.33
    Eventually
    0.33
     Belediyesi
    0.33
    曆
    0.33
     yaşayan
    0.33
    POSITIVE LOGITS
    良好
    0.63
     நன்றாக
    0.57
    良好的
    0.56
     अच्छी
    0.54
    大丈夫
    0.54
     بخير
    0.52
     satisfactory
    0.51
     excellently
    0.50
     alright
    0.49
     ổn
    0.49
    Activations Density 0.039%

    No Known Activations