© 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. 59172
    Prev
    Next
    INDEX
    Explanations

    urethra, ureter, urethane

    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
    s
    1.55
    การ
    1.46
    1
    1.36
    in
    1.27
     I
    1.27
     be
    1.19
    ם
    1.18
    EN
    1.13
    5
    1.12
    4
    1.06
    POSITIVE LOGITS
    ла
    1.30
    ен
    1.06
    んは
    1.05
    ong
    1.04
    ларга
    1.04
    。
    1.02
    مة
    1.01
    ib
    0.99
    ти
    0.99
    нку
    0.98
    Activations Density 0.000%

    No Known Activations