© 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. 199494
    Prev
    Next
    INDEX
    Explanations

    formal verb endings

    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
    그램
    0.53
    보니
    0.52
     보니
    0.45
    랗
    0.43
     නම්
    0.42
    グラム
    0.41
    வதில்
    0.41
    ktan
    0.41
    ran
    0.38
    либ
    0.38
    POSITIVE LOGITS
    Же
    0.42
    cheek
    0.41
    payable
    0.38
    త్య
    0.36
     ом
    0.36
    aima
    0.36
    墨
    0.35
    ppage
    0.34
     Же
    0.34
     эл
    0.33
    Activations Density 0.000%

    No Known Activations