© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24023
    Prev
    Next
    INDEX
    Explanations

    up

    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_56_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
     अ
    1.22
     به‌
    0.86
     עד
    0.86
    עד
    0.84
     update
    0.79
    update
    0.79
    อ
    0.77
     Update
    0.74
    Update
    0.72
    更新
    0.68
    POSITIVE LOGITS
     Up
    1.13
    Up
    1.04
     upp
    1.02
     UP
    1.02
    UP
    0.98
     Upp
    0.97
    Upp
    0.96
     업
    0.95
    업
    0.93
    アップ
    0.86
    Activations Density 0.002%

    No Known Activations