© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17301
    Prev
    Next
    INDEX
    Explanations

    Bulgarian

    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_40_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
     將
    0.40
    ęs
    0.40
     ହ
    0.38
    𝕦
    0.38
    ਸ਼
    0.37
    濟
    0.37
    ческий
    0.37
    老闆
    0.37
    割り
    0.37
    乌
    0.37
    POSITIVE LOGITS
     Bulgarian
    1.08
     Bulgaria
    0.98
     българ
    0.93
     Bulgar
    0.85
     Sofia
    0.84
     Bulg
    0.84
     България
    0.82
    Sofia
    0.76
     съ
    0.75
     дъл
    0.75
    Activations Density 0.002%

    No Known Activations