© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35241
    Prev
    Next
    INDEX
    Explanations

    instead of

    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_7_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
    щей
    0.73
    OUS
    0.71
    وم
    0.66
    шой
    0.64
    OVA
    0.62
    Gmail
    0.62
    ে
    0.61
    ленных
    0.61
    нення
    0.60
    μαν
    0.60
    POSITIVE LOGITS
     is
    0.90
    ita
    0.70
    ido
    0.68
    '
    0.65
     Lebensmittel
    0.64
    es
    0.64
    ič
    0.63
    iton
    0.63
    d
    0.62
    ís
    0.61
    Activations Density 0.049%

    No Known Activations