© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134128
    Prev
    Next
    INDEX
    Explanations

    worst case

    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_50_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
    pace
    0.51
     た
    0.44
    tu
    0.40
    prit
    0.40
    correct
    0.39
    rub
    0.39
    stun
    0.39
    ಿದ್ದು
    0.39
    cube
    0.38
    stencil
    0.38
    POSITIVE LOGITS
     nano
    0.40
    雔
    0.39
    句
    0.37
     possibilities
    0.37
    CharAt
    0.37
     cholesterol
    0.37
    ={()=>
    0.37
     groovy
    0.36
     ঝাঁপ
    0.36
     motorised
    0.36
    Activations Density 0.001%

    No Known Activations