© 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. 216182
    Prev
    Next
    INDEX
    Explanations

    Caribbean island destinations

    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
     Belize
    0.43
     pali
    0.37
    滪
    0.37
     খাজ
    0.36
     данного
    0.36
     रायपुर
    0.36
    legas
    0.36
     dict
    0.35
    ස්
    0.35
     Kev
    0.35
    POSITIVE LOGITS
    途
    0.43
    兮
    0.40
     Japón
    0.40
     Persians
    0.39
     জাপান
    0.39
     बर्थ
    0.39
     Япо
    0.38
    舱
    0.38
    Abroad
    0.38
    因子
    0.38
    Activations Density 0.001%

    No Known Activations