© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229468
    Prev
    Next
    INDEX
    Explanations

    place names and 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_6_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
    า
    0.95
    м
    0.92
    ה
    0.88
    ב
    0.88
    ко
    0.86
    й
    0.83
    ле
    0.81
    бо
    0.81
    то
    0.80
    е
    0.79
    POSITIVE LOGITS
     you
    1.08
    "
    0.86
    3
    0.79
    you
    0.76
    1
    0.75
     not
    0.74
     that
    0.74
     l
    0.73
    你
    0.73
     he
    0.72
    Activations Density 0.000%

    No Known Activations