© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100505
    Prev
    Next
    INDEX
    Explanations

    divina comedia

    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_14_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
    сон
    0.45
     warranties
    0.45
    ئ
    0.45
    문
    0.45
    nc
    0.44
    curr
    0.44
    toc
    0.44
    c
    0.44
    Islam
    0.44
    ки
    0.43
    POSITIVE LOGITS
     Расійскай
    0.49
     ජී
    0.49
     فانه
    0.49
     कोणत्याही
    0.48
     ¡
    0.48
     bestimmten
    0.48
     ▶
    0.48
    轸
    0.48
     長
    0.47
     半
    0.47
    Activations Density 0.000%

    No Known Activations