© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1190
    Prev
    Next
    INDEX
    Explanations

    function activation registration

    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_39_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
     Complexes
    0.44
     COMPLEXES
    0.43
    ཤ
    0.43
     হিস
    0.40
     gezogen
    0.40
    キャッシュ
    0.39
    竅
    0.38
    }}<
    0.38
    ONES
    0.38
    シップ
    0.37
    POSITIVE LOGITS
     Apollo
    0.42
     apre
    0.40
     alien
    0.40
     intranet
    0.39
     App
    0.38
    appy
    0.38
     APP
    0.38
     reproduc
    0.38
    append
    0.38
     euthan
    0.37
    Activations Density 0.000%

    No Known Activations