© 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. 34633
    Prev
    Next
    INDEX
    Explanations

    to hold

    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
     BACH
    0.40
    suk
    0.39
     Kris
    0.39
     Wain
    0.38
     Succ
    0.38
     Chicks
    0.38
    婹
    0.38
    薁
    0.37
     Chuk
    0.37
     Crusaders
    0.37
    POSITIVE LOGITS
     дер
    1.40
     drž
    1.20
     Держа
    1.18
     держать
    1.17
     Дер
    1.15
     держа
    1.14
     holding
    1.07
     Holding
    1.02
    Holding
    1.02
     DER
    1.01
    Activations Density 0.011%

    No Known Activations