© 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. 50579
    Prev
    Next
    INDEX
    Explanations

    polished

    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
    en
    0.50
    t
    0.46
    ant
    0.46
    in
    0.45
    d
    0.45
    ar
    0.44
    a
    0.44
    b
    0.44
    et
    0.43
    ad
    0.43
    POSITIVE LOGITS
    ྛ
    0.29
    ꩡ
    0.28
     Пе
    0.28
     ontwikkelen
    0.26
    ؟.
    0.26
    Три
    0.26
    比特币
    0.25
     Кі
    0.25
     চলচ্
    0.25
     ప్రారంభ
    0.25
    Activations Density 0.007%

    No Known Activations