© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58141
    Prev
    Next
    INDEX
    Explanations

    medical instrument suffixes like -scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    t
    1.90
    től
    1.38
    taker
    1.35
    ших
    1.29
    s
    1.27
    k
    1.17
    kör
    1.15
    ний
    1.14
    n
    1.13
    tch
    1.12
    POSITIVE LOGITS
    1.37
     في
    1.34
     в
    1.32
    п
    1.21
    A
    1.16
    In
    1.15
    \]
    1.09
    在
    1.09
    ı
    1.08
    H
    1.06
    Activations Density 0.001%

    No Known Activations