© 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. 53598
    Prev
    Next
    INDEX
    Explanations

    Myanmar, Asian nation

    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
     hindi
    0.40
     الوحد
    0.38
    दर्भ
    0.37
    寞
    0.37
    Planner
    0.37
    ចូល
    0.36
    க்கில்
    0.35
     mutlu
    0.35
    埥
    0.35
    颍
    0.34
    POSITIVE LOGITS
    streetmap
    0.41
    ghijkl
    0.39
    州市
    0.39
     うん
    0.38
     verbose
    0.37
    sqlite
    0.37
    bbb
    0.37
    ুকের
    0.37
     capacitive
    0.36
     laissent
    0.36
    Activations Density 0.001%

    No Known Activations