© 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
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223736
    Prev
    Next
    INDEX
    Explanations

    and then

    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_10_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
    and
    0.61
    ou
    0.55
    c
    0.53
     belirli
    0.50
    v
    0.50
    on
    0.48
    ;
    0.48
    ü
    0.47
    Phone
    0.47
     futuro
    0.45
    POSITIVE LOGITS
    대의
    0.51
     ними
    0.48
    خدام
    0.46
    euros
    0.45
     pulsating
    0.45
    dominant
    0.44
    ভাষায়
    0.44
    persistent
    0.44
    pyrim
    0.43
    대를
    0.43
    Activations Density 0.003%

    No Known Activations