© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131556
    Prev
    Next
    INDEX
    Explanations

    car

    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
    萊
    0.41
     Рим
    0.39
     Nicole
    0.39
    ptive
    0.39
    caria
    0.38
    лен
    0.38
    ilj
    0.38
    <unused25>
    0.38
    aic
    0.37
     heard
    0.37
    POSITIVE LOGITS
     invertebrates
    0.41
     D
    0.40
    azza
    0.40
     Mog
    0.39
    Դ
    0.39
    sects
    0.38
     Gifford
    0.38
     sixty
    0.38
     interstitials
    0.38
     করাতে
    0.38
    Activations Density 0.001%

    No Known Activations