© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170256
    Prev
    Next
    INDEX
    Explanations

    vibe check

    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_20_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
     kelamin
    0.39
     ክ
    0.38
    npy
    0.38
     pantalones
    0.37
     пар
    0.36
    ulloch
    0.34
     đảng
    0.34
     pants
    0.33
     puns
    0.33
    ลาด
    0.33
    POSITIVE LOGITS
    año
    0.40
    define
    0.40
    三
    0.40
     डाई
    0.38
    from
    0.38
     passado
    0.38
    stop
    0.37
    ultimo
    0.37
     System
    0.37
    för
    0.36
    Activations Density 0.006%

    No Known Activations