© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16215
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and officials

    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_40_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
     dvar
    0.47
     Superior
    0.41
    Superior
    0.41
    fv
    0.39
    PanelView
    0.39
     ड
    0.38
     pack
    0.38
     superior
    0.38
    GFR
    0.38
    Divine
    0.37
    POSITIVE LOGITS
    DBG
    0.42
    चर्स
    0.39
    プレゼ
    0.37
     proposal
    0.36
     cogniz
    0.35
     malaise
    0.35
    研
    0.35
     proclam
    0.35
     lands
    0.34
    ulen
    0.34
    Activations Density 0.001%

    No Known Activations