© 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. 75735
    Prev
    Next
    INDEX
    Explanations

    Chinese civil war

    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
     মুসল
    0.40
    峣
    0.40
     сообще
    0.39
     книг
    0.39
     нейтра
    0.39
    ቾ
    0.39
     macrom
    0.38
     Bonif
    0.38
    Transition
    0.37
    萂
    0.37
    POSITIVE LOGITS
    ulose
    0.39
    underline
    0.36
    pair
    0.36
    (*)
    0.34
    per
    0.34
    trem
    0.34
    ular
    0.34
    álny
    0.34
    别
    0.34
    baidu
    0.34
    Activations Density 0.002%

    No Known Activations