© 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. 199445
    Prev
    Next
    INDEX
    Explanations

    stories

    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
    代
    0.37
    伍章
    0.37
     manhood
    0.37
    英
    0.36
     freshness
    0.36
     Woodrow
    0.36
    而
    0.36
     לס
    0.36
    ievo
    0.35
     Seward
    0.35
    POSITIVE LOGITS
    eer
    0.43
    ступ
    0.41
    ব্যাপী
    0.41
    eers
    0.39
    рте
    0.39
    oked
    0.38
    erre
    0.38
    izards
    0.38
     लागले
    0.38
    겔
    0.38
    Activations Density 0.000%

    No Known Activations