© 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. 199949
    Prev
    Next
    INDEX
    Explanations

    fictional characters

    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
    Raj
    0.40
    +|\
    0.38
    योगी
    0.38
    !='
    0.37
    етки
    0.37
     chromatographed
    0.36
     handeln
    0.36
    referer
    0.35
    alek
    0.35
    oderm
    0.35
    POSITIVE LOGITS
    ッフ
    0.46
     Que
    0.39
     राष्ट
    0.39
     Trash
    0.38
     rou
    0.38
    露
    0.38
     Appearance
    0.38
    শাস
    0.37
    घ्र
    0.35
     Heel
    0.35
    Activations Density 0.000%

    No Known Activations