© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88764
    Prev
    Next
    INDEX
    Explanations

    (x, y, w, h) coordinates

    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_23_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
     fr
    0.48
    fr
    0.43
        
    0.42
     ク
    0.41
     Fr
    0.40
      
    0.38
     INTER
    0.38
    Prefab
    0.38
    amu
    0.38
         
    0.38
    POSITIVE LOGITS
    跚
    0.45
    निश्ड
    0.44
     vattum
    0.44
     primeiras
    0.43
     antiguas
    0.43
    мония
    0.43
     философия
    0.42
     sendo
    0.42
     organizações
    0.41
     стоимо
    0.41
    Activations Density 0.000%

    No Known Activations