© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17467
    Prev
    Next
    INDEX
    Explanations

    cv2.imread

    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_40_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
    ゼ
    0.35
    
    0.35
    ursive
    0.34
     පි
    0.33
     `<=
    0.33
     এলাম
    0.33
    writeFileSync
    0.33
    回
    0.33
    aguchi
    0.33
     geese
    0.33
    POSITIVE LOGITS
     unchanged
    0.81
     unaltered
    0.66
     unchanging
    0.58
    不变
    0.52
    unch
    0.50
     cambiado
    0.48
     değiş
    0.47
    変わ
    0.44
     changed
    0.44
     unmodified
    0.43
    Activations Density 0.001%

    No Known Activations