© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44748
    Prev
    Next
    INDEX
    Explanations

    -ism, -ist, Time, Breath

    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_13_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
     Dateien
    0.56
    ্রে
    0.56
     konkre
    0.53
    盡
    0.53
     Ideen
    0.50
    H
    0.50
    原创
    0.50
    С
    0.49
     travaux
    0.49
     Kön
    0.49
    POSITIVE LOGITS
    izquierda
    0.49
    ین
    0.47
     ایک
    0.46
     sausage
    0.45
     choked
    0.45
    t
    0.45
    olinha
    0.44
    τή
    0.43
     கார
    0.43
     جیسا
    0.43
    Activations Density 0.000%

    No Known Activations