© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228625
    Prev
    Next
    INDEX
    Explanations

    Indonesian conversation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     baik
    0.55
     Baik
    0.49
    Baik
    0.43
    baik
    0.42
     oku
    0.40
    या
    0.40
    put
    0.40
    顯
    0.39
    显
    0.39
    ień
    0.38
    POSITIVE LOGITS
    Kam
    0.68
     Kam
    0.63
     kam
    0.61
    Cam
    0.57
    kam
    0.55
     KAM
    0.55
    KAM
    0.54
    mu
    0.50
     Cam
    0.50
    Ny
    0.50
    Activations Density 0.000%

    No Known Activations