© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24364
    Prev
    Next
    INDEX
    Explanations

    information, models, language, description

    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
     in
    0.16
    A
    0.16
    在
    0.16
    0.15
    ın
    0.15
    é
    0.14
    的
    0.14
    ные
    0.14
    s
    0.14
    ığını
    0.13
    POSITIVE LOGITS
    نې
    0.17
     informacije
    0.16
     arasında
    0.15
     przyjem
    0.14
     achet
    0.14
    
    0.13
     〢
    0.13
     modele
    0.13
     amplifier
    0.13
     layak
    0.13
    Activations Density 0.133%

    No Known Activations