© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64025
    Prev
    Next
    INDEX
    Explanations

    Google Docs and Sheets

    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_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
    rosine
    0.49
    Liz
    0.42
     sorption
    0.41
     Arthur
    0.40
    вость
    0.40
    LevelLinking
    0.40
    firmasi
    0.38
    釉
    0.38
     cig
    0.38
    Rosen
    0.38
    POSITIVE LOGITS
     Google
    1.92
    Google
    1.86
     google
    1.74
     গুগল
    1.55
     گوگل
    1.55
     गूगल
    1.53
    google
    1.52
    谷歌
    1.40
    GOOGLE
    1.40
     Goog
    1.33
    Activations Density 0.009%

    No Known Activations