© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172039
    Prev
    Next
    INDEX
    Explanations

    organizations and job titles

    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_20_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
    த்துள்ளார்
    0.20
     ছয়
    0.20
    عی
    0.20
     처음
    0.19
     nội
    0.19
     협
    0.19
     przys
    0.19
     இடம்பெ
    0.19
    ۶
    0.19
     bầu
    0.19
    POSITIVE LOGITS
     voucher
    0.20
    considered
    0.20
    💴
    0.20
    Sanchez
    0.19
     where
    0.19
     interesar
    0.19
     منسلک
    0.19
     DeS
    0.18
     WC
    0.18
     ఉన్నాయి
    0.18
    Activations Density 0.009%

    No Known Activations