© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 11803
    Prev
    Next
    INDEX
    Explanations

    Hitchhiker's Guide to the Galaxy

    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_13_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
    ي
    0.16
     rares
    0.13
    న్
    0.12
     outings
    0.12
     vices
    0.12
     رغم
    0.12
    ्रेडिट
    0.12
     часов
    0.12
    ק
    0.11
    و
    0.11
    POSITIVE LOGITS
    xml
    0.14
     XML
    0.13
     בה
    0.12
    :</
    0.12
     xml
    0.12
     khẩu
    0.11
     首先
    0.11
     SETUP
    0.11
    蜥
    0.11
    DICTION
    0.11
    Activations Density 0.006%

    No Known Activations