© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153996
    Prev
    Next
    INDEX
    Explanations

    say "state"

    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_60_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
    MathMarks
    0.41
     s
    0.40
    feed
    0.40
     chromedp
    0.40
    floor
    0.40
     tassels
    0.39
    persons
    0.38
     wild
    0.38
    tour
    0.38
     thailand
    0.37
    POSITIVE LOGITS
     S
    0.92
     state
    0.88
     State
    0.86
    S
    0.83
    STATE
    0.80
    State
    0.75
     С
    0.73
    𝑆
    0.72
     STATE
    0.71
     Secure
    0.71
    Activations Density 0.000%

    No Known Activations