© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3212
    Prev
    Next
    INDEX
    Explanations

    case statements

    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_39_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
     opposite
    0.39
     건축
    0.39
    opposite
    0.38
    虺
    0.38
    olim
    0.37
     contrario
    0.36
     contraire
    0.36
    温暖
    0.36
    反而
    0.36
     നി
    0.36
    POSITIVE LOGITS
     hesitate
    0.40
     Formatting
    0.40
     hesitated
    0.38
     formatting
    0.36
     Potatoes
    0.35
     Verw
    0.35
    hes
    0.35
    ♥
    0.34
    Welcome
    0.33
    ChartView
    0.33
    Activations Density 0.002%

    No Known Activations