© 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. 166502
    Prev
    Next
    INDEX
    Explanations

    scores and results

    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
     प्रति
    0.39
     مشاهد
    0.37
     torpedo
    0.36
     maxHeight
    0.35
     Exc
    0.35
    CHEN
    0.34
    阈
    0.34
     EXPL
    0.34
    keleton
    0.34
     threshold
    0.33
    POSITIVE LOGITS
    yty
    0.37
    하다
    0.37
    
    0.37
    옛
    0.35
     eftersom
    0.35
    ouer
    0.35
     옛
    0.34
    alate
    0.34
     beide
    0.33
    arsi
    0.33
    Activations Density 0.000%

    No Known Activations