© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30545
    Prev
    Next
    INDEX
    Explanations

    ai.google.dev/gemma

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     எழுந்த
    0.37
     coron
    0.36
    ும்போது
    0.35
    듬
    0.34
    andro
    0.34
     lanjutkan
    0.34
     Coron
    0.34
    ://
    0.33
     WEIGHT
    0.33
     leaf
    0.33
    POSITIVE LOGITS
    珑
    0.36
     स्वरूप
    0.35
    oblins
    0.35
    MCs
    0.35
     së
    0.34
    AMENT
    0.33
     चलो
    0.33
    తున్నారు
    0.33
    zIndex
    0.33
    haut
    0.33
    Activations Density 0.011%

    No Known Activations