© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218972
    Prev
    Next
    INDEX
    Explanations

    Indian states and US states

    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
     海外
    0.41
    solid
    0.39
    centi
    0.38
    PropertyName
    0.37
     твер
    0.34
    (".");
    0.34
    quin
    0.34
     இருக்க
    0.34
     √
    0.33
    Mos
    0.33
    POSITIVE LOGITS
     Nebraska
    0.52
     बिहार
    0.45
     Eintritt
    0.45
     florida
    0.42
     jez
    0.42
     Illinois
    0.42
     Arizona
    0.41
     Bihar
    0.41
    らかじめ
    0.41
     ಕರ್ನಾಟಕ
    0.41
    Activations Density 0.002%

    No Known Activations