© 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. 34704
    Prev
    Next
    INDEX
    Explanations

    Dutch culture and music

    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
     verst
    0.45
    ++];
    0.42
    <0x89>
    0.40
     JFrame
    0.40
     प्रथ
    0.39
    ྤ
    0.39
     স্ম
    0.39
    oplasty
    0.39
    #
    0.38
    п
    0.38
    POSITIVE LOGITS
     bon
    0.44
    Bon
    0.40
    कार
    0.39
    Tos
    0.38
    Gab
    0.37
     Bon
    0.37
    bon
    0.36
    Sche
    0.36
     एपल
    0.36
    Rot
    0.36
    Activations Density 0.002%

    No Known Activations