© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67249
    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_41_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
     tail
    0.71
     tailed
    0.63
     tails
    0.59
    tail
    0.57
    tailed
    0.57
    Tail
    0.57
    尾
    0.54
     Tail
    0.50
     хво
    0.49
     Tails
    0.49
    POSITIVE LOGITS
    മ്
    0.40
    瘸
    0.34
     schneller
    0.34
     LTD
    0.34
     hemic
    0.34
    丞
    0.34
    仇
    0.33
     ederim
    0.33
     ژ
    0.33
    မ္
    0.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.