© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221387
    Prev
    Next
    INDEX
    Explanations

    nationalism and political ideologies

    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_10_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
     $
    0.57
     molded
    0.55
     Caesar
    0.54
     Echo
    0.54
     first
    0.52
     pressurized
    0.52
     slightly
    0.51
     कर्ण
    0.50
     adapted
    0.49
     GO
    0.49
    POSITIVE LOGITS
    儒
    0.52
    뗀
    0.50
    
    0.47
    منٹ
    0.46
    錯
    0.45
     gratuitamente
    0.44
    байд
    0.44
    聊天
    0.43
    嗦
    0.42
    preprocess
    0.42
    Activations Density 0.000%

    No Known Activations