© 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. 133279
    Prev
    Next
    INDEX
    Explanations

    customs and import

    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
    Purg
    0.43
    atrice
    0.41
    Hall
    0.40
    es
    0.39
    كاته
    0.38
    ('/:
    0.38
    ات
    0.37
    koa
    0.37
    $',
    0.37
    koľ
    0.36
    POSITIVE LOGITS
     cons
    0.38
     cli
    0.38
     CLIN
    0.36
    我就
    0.36
     thận
    0.35
     touching
    0.35
     betterment
    0.35
     mismanagement
    0.35
     స్థ
    0.34
     Adaptive
    0.34
    Activations Density 0.001%

    No Known Activations