© 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. 80347
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    写法
    0.44
    迟
    0.42
     пос
    0.37
    秵
    0.36
     મુ
    0.36
     belated
    0.36
    つ
    0.35
     pres
    0.35
     ;
    0.35
    遅
    0.35
    POSITIVE LOGITS
     balancing
    0.44
     پولیس
    0.37
     než
    0.37
    oje
    0.37
     puts
    0.36
     peptides
    0.35
    łąd
    0.35
     motivates
    0.34
     বলিউ
    0.34
     UG
    0.34
    Activations Density 0.000%

    No Known Activations