© 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
    2. Gemma-3-27B-IT
    3. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 16521
    Prev
    Next
    INDEX
    Explanations

    model

    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_15_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
     Dang
    0.61
     w
    0.50
     tool
    0.50
     H
    0.50
     R
    0.49
    ény
    0.49
     PO
    0.49
     h
    0.48
    arq
    0.48
     ir
    0.48
    POSITIVE LOGITS
     ব্যবসার
    0.54
    ой
    0.48
    ibfk
    0.48
     অবস্থানে
    0.46
    toBottomOf
    0.46
     সংকো
    0.46
     বিপর
    0.45
    꼼
    0.45
    ਿਆ
    0.45
     obč
    0.45
    Activations Density 0.022%

    No Known Activations