© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85393
    Prev
    Next
    INDEX
    Explanations

    modelparameters, ratio, parameters

    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_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
    یک
    0.77
    ید
    0.74
    ه
    0.71
    ਨ
    0.68
    یل
    0.67
    ס
    0.67
    that
    0.66
    تان
    0.64
    ਰ
    0.64
    𝗵
    0.63
    POSITIVE LOGITS
     in
    0.81
     verwend
    0.75
     bestaat
    0.70
     weten
    0.68
     في
    0.68
     kwam
    0.65
    0.64
     hiszen
    0.63
     كبير
    0.62
     modelu
    0.61
    Activations Density 0.012%

    No Known Activations