© 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. 58116
    Prev
    Next
    INDEX
    Explanations

    yawl

    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
     (
    1.26
    i
    1.19
    s
    1.16
    that
    1.09
    ।
    0.98
     I
    0.96
    ి
    0.93
    י
    0.89
    ру
    0.87
    んで
    0.87
    POSITIVE LOGITS
    ج
    1.13
    0
    1.08
    nál
    1.07
    मधील
    1.02
    ა
    1.02
    ON
    1.02
     súa
    1.00
     riječi
    0.93
    '
    0.93
    ਰ
    0.93
    Activations Density 0.000%

    No Known Activations