© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35424
    Prev
    Next
    INDEX
    Explanations

    Okay

    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_31_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
    лум
    0.43
     સંદ
    0.41
    yCoordinate
    0.40
     hydrophilic
    0.39
     humide
    0.38
    zne
    0.38
    шим
    0.37
    阏
    0.36
    ொட
    0.36
    갠
    0.36
    POSITIVE LOGITS
     Afterward
    0.42
     Perhaps
    0.41
     Simply
    0.41
     Investig
    0.39
     Corporations
    0.39
     Workers
    0.39
     Cata
    0.39
     deliberately
    0.38
     Camping
    0.38
     reu
    0.38
    Activations Density 0.059%

    No Known Activations