© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259683
    Prev
    Next
    INDEX
    Explanations

    QA V

    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_22_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
     ਯ
    0.23
    StartY
    0.23
     ثقاف
    0.23
    尿
    0.22
     அதிகமான
    0.22
    estone
    0.21
    検討
    0.21
     فرهنگ
    0.21
    AMP
    0.21
     البدايه
    0.20
    POSITIVE LOGITS
     formidable
    0.24
     bolet
    0.23
    ж
    0.23
    ável
    0.23
    ovej
    0.22
     collier
    0.22
    ary
    0.22
     nonfiction
    0.22
    де
    0.22
    .${
    0.22
    Activations Density 0.013%

    No Known Activations