© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162475
    Prev
    Next
    INDEX
    Explanations

    city names

    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
    Sweden
    0.40
    bouncer
    0.39
     confined
    0.38
     Republic
    0.37
     Apps
    0.36
    woods
    0.36
    Noir
    0.36
    립
    0.36
    ورو
    0.35
    Labs
    0.35
    POSITIVE LOGITS
     cidades
    0.47
     города
    0.46
     miasta
    0.46
     शहरा
    0.46
     ciudades
    0.45
     городах
    0.45
     města
    0.44
     शहरों
    0.43
     도시
    0.43
     cidade
    0.43
    Activations Density 0.005%

    No Known Activations