© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217924
    Prev
    Next
    INDEX
    Explanations

    Ten-Day War, Sha La La, Double Cross

    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
    Č
    0.54
    Š
    0.51
    ž
    0.49
    ší
    0.48
    ží
    0.48
    Ž
    0.48
    žiť
    0.47
    žić
    0.47
    šan
    0.47
     Józ
    0.47
    POSITIVE LOGITS
     Rfc
    0.41
     Nbd
    0.39
     कंटिन्यू
    0.39
    扇
    0.37
     الأمريكي
    0.36
     Wash
    0.35
     continual
    0.35
     Cher
    0.35
     contingent
    0.35
     độc
    0.35
    Activations Density 0.007%

    No Known Activations