© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35634
    Prev
    Next
    INDEX
    Explanations

    factor/agent

    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_50_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
     Ar
    0.60
     ار
    0.60
     ar
    0.58
    Ar
    0.56
     أر
    0.55
    漃
    0.49
     الار
    0.47
     ар
    0.47
    ндай
    0.47
    椃
    0.47
    POSITIVE LOGITS
     عامل
    0.92
     والع
    0.84
     factor
    0.75
     للع
    0.70
     Factor
    0.68
    Factor
    0.66
    factor
    0.64
     facteur
    0.63
     العامل
    0.63
     फैक्टर
    0.63
    Activations Density 0.001%

    No Known Activations