© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148241
    Prev
    Next
    INDEX
    Explanations

    HTML 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_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
    tte
    0.42
     %
    0.40
    страи
    0.40
    }$=
    0.39
     হলেন
    0.38
     ><
    0.38
     barcode
    0.37
    tter
    0.37
    $>
    0.36
     .
    0.35
    POSITIVE LOGITS
    凜
    0.44
    -"
    0.40
    hepatic
    0.38
    though
    0.38
    Finn
    0.38
    LinkedList
    0.38
    ="${
    0.38
     때문
    0.37
    -'
    0.37
    LCD
    0.37
    Activations Density 0.001%

    No Known Activations