© 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. 34329
    Prev
    Next
    INDEX
    Explanations

    Ber

    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
     Ley
    0.40
     крайней
    0.38
     noc
    0.38
     nop
    0.36
    jer
    0.36
    )=(
    0.35
    ्युन
    0.35
    櫂
    0.35
     itens
    0.34
     Lyons
    0.34
    POSITIVE LOGITS
    起動
    0.42
     scenario
    0.40
     elongation
    0.40
    zi
    0.40
    scenario
    0.40
    achi
    0.39
    بن
    0.39
    iqui
    0.38
    Urs
    0.38
     zipper
    0.38
    Activations Density 0.000%

    No Known Activations