© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15053
    Prev
    Next
    INDEX
    Explanations

    geolocation and accuracy

    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_15_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
    ig
    0.59
    ↵
    0.56
    us
    0.55
    ver
    0.53
    ul
    0.52
     r
    0.50
     C
    0.49
    ed
    0.49
    age
    0.49
    rom
    0.48
    POSITIVE LOGITS
     yǔ
    0.53
    বছ
    0.48
    oitte
    0.48
    ेलकम
    0.47
    LNG
    0.46
    OECD
    0.46
    Ϟ
    0.46
     പദ്ധതി
    0.46
     IMHO
    0.46
     एक्चु
    0.45
    Activations Density 0.001%

    No Known Activations