© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93238
    Prev
    Next
    INDEX
    Explanations

    resource guarantee

    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_11_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
    normalized
    0.57
    Н
    0.54
     রাষ্ট্রীয়
    0.54
    O
    0.54
    ST
    0.53
    يب
    0.53
    лик
    0.53
    ī
    0.52
    не
    0.52
    Normalized
    0.52
    POSITIVE LOGITS
     trustees
    0.65
     pastors
    0.64
     curators
    0.59
     Ulster
    0.58
    ဟုတ်
    0.57
    াপতি
    0.57
    ğini
    0.57
    केशन
    0.56
     Mike
    0.55
     trustee
    0.55
    Activations Density 0.001%

    No Known Activations