© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174745
    Prev
    Next
    INDEX
    Explanations

    fairly or protection

    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_20_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
     órdenes
    0.50
     বক্তব
    0.48
    ヱ
    0.48
    buildSpec
    0.47
     suppressing
    0.47
     गिवन
    0.46
     இம்ம
    0.46
    GALAD
    0.46
     ganglions
    0.45
    (([
    0.44
    POSITIVE LOGITS
    ward
    0.52
    ness
    0.43
     ca
    0.42
     en
    0.42
    iske
    0.42
    !)
    0.42
    maal
    0.41
    IV
    0.41
    ca
    0.41
    Common
    0.41
    Activations Density 0.000%

    No Known Activations