© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204027
    Prev
    Next
    INDEX
    Explanations

    filtering data

    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_37_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
    صاف
    0.43
     жидко
    0.42
    焘
    0.40
    情報は
    0.40
    内容的
    0.38
    ucco
    0.37
     localised
    0.36
     oversight
    0.36
    MATRIX
    0.36
     puedan
    0.36
    POSITIVE LOGITS
    good
    0.39
    stress
    0.38
     elimination
    0.38
     исклю
    0.37
     surrounded
    0.37
     ?-
    0.37
     चांग
    0.36
    haria
    0.36
     Caught
    0.36
     élim
    0.36
    Activations Density 0.001%

    No Known Activations