© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194806
    Prev
    Next
    INDEX
    Explanations

    UI commands and navigation

    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_27_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
     staff
    0.38
     usando
    0.37
     Sponsored
    0.37
     utilizando
    0.36
     (@
    0.36
     사용하는
    0.35
     using
    0.35
     কর্মচার
    0.35
    時間
    0.35
     utilizing
    0.34
    POSITIVE LOGITS
    dsale
    0.49
    toggle
    0.46
     toggle
    0.44
    tog
    0.42
    движи
    0.42
    縊
    0.42
     narrowing
    0.41
     burial
    0.39
    tapping
    0.39
    arrivalTime
    0.38
    Activations Density 0.034%

    No Known Activations