© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9070
    Prev
    Next
    INDEX
    Explanations

    not seen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    우리
    0.87
    Este
    0.87
    요
    0.85
     understandable
    0.83
    yya
    0.80
    yy
    0.80
    ड
    0.79
     exuber
    0.79
    แสดง
    0.77
    aac
    0.77
    POSITIVE LOGITS
    м
    0.92
     sina
    0.70
    configFile
    0.70
    തിരെ
    0.69
     wanting
    0.69
     rave
    0.69
    侶
    0.68
    ніх
    0.68
    keepers
    0.66
     skle
    0.65
    Activations Density 0.000%

    No Known Activations