© 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. 121682
    Prev
    Next
    INDEX
    Explanations

    pressure release

    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
    at
    1.01
    ،
    0.73
     to
    0.71
    w
    0.67
    atief
    0.66
    ül
    0.66
    رة
    0.65
    était
    0.64
    اپ
    0.64
    water
    0.63
    POSITIVE LOGITS
    ↵
    0.72
    ട്ടില്‍
    0.62
     personaggi
    0.61
     impor
    0.61
     debounce
    0.57
     thisStudent
    0.55
    abcdef
    0.55
     sympy
    0.54
     *
    0.53
    debounce
    0.53
    Activations Density 0.001%

    No Known Activations