© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36795
    Prev
    Next
    INDEX
    Explanations

    array sorting 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_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
     Unternehmens
    0.42
    endaten
    0.41
    
    0.39
    ">+
    0.39
    垻
    0.38
    ᑖ
    0.38
     cotidiana
    0.38
     ভাবতে
    0.37
    스를
    0.37
    ">-
    0.37
    POSITIVE LOGITS
    Perry
    0.41
    oo
    0.40
    o
    0.38
    so
    0.38
     Perry
    0.36
     fixtures
    0.34
    odo
    0.34
    <0xC2>
    0.33
    amilton
    0.33
    diag
    0.33
    Activations Density 0.002%

    No Known Activations