© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133478
    Prev
    Next
    INDEX
    Explanations

    Indonesian greetings/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_1_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
    ন
    1.45
    ن
    1.43
    I
    1.30
    ।
    1.25
    न
    1.21
    ING
    1.16
    िंग
    1.12
    al
    1.03
     ।
    1.03
    ing
    1.02
    POSITIVE LOGITS
    ка
    1.17
    даги
    1.05
    dą
    1.05
    t
    1.05
    gambar
    1.04
    ம்
    1.03
    ၃
    1.03
    diği
    1.00
    ၅
    1.00
    га
    0.98
    Activations Density 0.000%

    No Known Activations