© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101459
    Prev
    Next
    INDEX
    Explanations

    Huygens, Main Memory, rows, portrayed, wave, numpy

    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_16_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
    }
    0.53
    נון
    0.52
    язку
    0.51
    ಭಾ
    0.48
    砊
    0.48
    ukuran
    0.47
     inden
    0.47
    㭉
    0.46
    $(\
    0.46
    лейбол
    0.46
    POSITIVE LOGITS
     coerce
    0.52
    ǎo
    0.49
     superbly
    0.49
     exacerbate
    0.47
    島の
    0.46
     Gave
    0.45
     avoid
    0.45
     educate
    0.45
     deceive
    0.45
    нув
    0.45
    Activations Density 0.000%

    No Known Activations