© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161601
    Prev
    Next
    INDEX
    Explanations

    Earnings Release

    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_31_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
    णा
    0.38
    ljeni
    0.38
    覤
    0.38
    ței
    0.38
    íf
    0.37
    nými
    0.37
    欝
    0.37
    ným
    0.37
    urança
    0.36
    ój
    0.36
    POSITIVE LOGITS
     ostensibly
    0.34
     locales
    0.33
     linked
    0.33
     mock
    0.31
    ('/:
    0.31
     locale
    0.31
     ply
    0.31
     battles
    0.30
     Москвы
    0.30
     war
    0.29
    Activations Density 0.001%

    No Known Activations