© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3927
    Prev
    Next
    INDEX
    Explanations

    permissions for ACCESS

    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_39_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
    ভাসের
    0.46
     gg
    0.42
     whitish
    0.40
     raged
    0.40
    㔯
    0.40
     Anita
    0.39
     blooms
    0.39
    Rhe
    0.38
     Hick
    0.38
     ank
    0.37
    POSITIVE LOGITS
     seven
    0.42
    七
    0.42
     siete
    0.40
    parsed
    0.39
     MAX
    0.39
     Seven
    0.39
     هفت
    0.39
     WY
    0.38
     ஏழு
    0.38
     七
    0.37
    Activations Density 0.002%

    No Known Activations