© 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. 33238
    Prev
    Next
    INDEX
    Explanations

    IR, RO, or NG at start of words

    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
     for
    0.82
    s
    0.82
    st
    0.71
    "))
    0.63
     de
    0.59
    oly
    0.59
     הולנד
    0.58
    }
    0.58
    Data
    0.57
     eluted
    0.57
    POSITIVE LOGITS
    но
    0.84
    ى
    0.79
    ли
    0.79
    ки
    0.71
    ला
    0.68
    た
    0.68
    내
    0.67
    жён
    0.65
    ல
    0.64
    制定
    0.61
    Activations Density 0.001%

    No Known Activations