© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57677
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_59_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
    hitth
    0.41
    мые
    0.41
    颀
    0.38
     Caedwalla
    0.38
    uelo
    0.38
     crust
    0.37
    щают
    0.37
     prestaciones
    0.37
    yect
    0.36
    拽
    0.36
    POSITIVE LOGITS
       
    0.55
    two
    0.55
     ----
    0.55
     -----
    0.50
     ----------
    0.48
     Two
    0.47
    five
    0.47
    eight
    0.47
         
    0.47
     -------------
    0.46
    Activations Density 0.003%

    No Known Activations