© 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. 195230
    Prev
    Next
    INDEX
    Explanations

    place names or foreign words

    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
     be
    0.57
     特
    0.53
     ت
    0.52
     এক
    0.52
     பகு
    0.52
     Exploration
    0.52
     সমাবেশে
    0.52
     குடியிருப்ப
    0.52
     விரிவா
    0.51
     \
    0.50
    POSITIVE LOGITS
     animali
    0.56
    Animals
    0.55
    水果
    0.55
     animals
    0.53
     zelen
    0.51
     chocolat
    0.50
     Animals
    0.48
    animals
    0.47
     Birds
    0.46
    葭
    0.46
    Activations Density 0.000%

    No Known Activations