© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166792
    Prev
    Next
    INDEX
    Explanations

    my

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     leg
    0.45
    leg
    0.43
    ^{*}$-
    0.41
    LEG
    0.41
    elter
    0.39
     lég
    0.38
     Leg
    0.38
     Shil
    0.37
    ු
    0.36
     boss
    0.36
    POSITIVE LOGITS
     date
    0.46
     мать
    0.45
    Line
    0.45
     witnesses
    0.44
    Mother
    0.44
     Role
    0.44
     mère
    0.44
     Line
    0.43
    Date
    0.43
    Role
    0.43
    Activations Density 0.002%

    No Known Activations