© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91174
    Prev
    Next
    INDEX
    Explanations

    Motor, stool, nail, array

    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_3_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
    (
    0.67
    ти
    0.64
    de
    0.64
    -
    0.64
     a
    0.57
     Xamarin
    0.57
    orient
    0.55
     reformulation
    0.55
    <0x80>
    0.54
    ung
    0.53
    POSITIVE LOGITS
     to
    0.70
    কে
    0.70
    RA
    0.67
     dangereux
    0.62
     at
    0.61
    PA
    0.59
    PRODUCT
    0.58
    İN
    0.57
    ш
    0.56
    도
    0.56
    Activations Density 0.000%

    No Known Activations