© 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. 166979
    Prev
    Next
    INDEX
    Explanations

    temporal indicators

    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
     Note
    0.41
     Hum
    0.39
    uling
    0.38
     Slab
    0.38
     Server
    0.37
    **********
    0.36
     Groups
    0.36
    रोक
    0.35
     Tempo
    0.35
     twisted
    0.35
    POSITIVE LOGITS
     colleg
    0.40
    ACM
    0.38
    Inicio
    0.38
    because
    0.38
     बिकॉज
    0.38
     bbox
    0.37
    AspNetCore
    0.36
    fiction
    0.36
    超
    0.36
     เจอ
    0.36
    Activations Density 0.000%

    No Known Activations