© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54821
    Prev
    Next
    INDEX
    Explanations

    preview code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     provoke
    0.37
    赓
    0.37
     commotion
    0.37
     diligence
    0.36
     prohibitions
    0.36
     mitigation
    0.35
     poursuivre
    0.35
     प्रभारी
    0.35
     provocation
    0.35
     validations
    0.35
    POSITIVE LOGITS
    ().
    0.43
    =".$
    0.42
    ->
    0.42
    (){
    0.41
    =(
    0.40
     ->
    0.39
    ','#
    0.38
    ._
    0.38
    )){
    0.38
    ‌ترین
    0.37
    Activations Density 0.001%

    No Known Activations