© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61745
    Prev
    Next
    INDEX
    Explanations

    cities and towns

    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_59_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
     примере
    0.36
    ี่ย
    0.36
    orschung
    0.36
    ுகள்
    0.35
    య్య
    0.35
    blurred
    0.35
     காரண
    0.35
    制
    0.34
    ､
    0.34
    すぎる
    0.34
    POSITIVE LOGITS
     city
    1.70
     town
    1.63
     City
    1.48
    city
    1.37
     città
    1.36
    City
    1.29
     CITY
    1.29
     город
    1.24
     cidade
    1.21
     village
    1.20
    Activations Density 0.010%

    No Known Activations