© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221518
    Prev
    Next
    INDEX
    Explanations

    numbers and units (px, ms, 0)

    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_10_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
    लिसिस
    0.29
     MOSFET
    0.28
     DQN
    0.28
    ።
    0.28
     looping
    0.27
    。</
    0.27
     starfish
    0.26
     chimpan
    0.26
    粝
    0.26
     dataframe
    0.26
    POSITIVE LOGITS
    s
    0.44
    I
    0.38
    v
    0.35
    x
    0.35
    W
    0.31
    C
    0.31
    R
    0.30
    ี
    0.30
    B
    0.29
    ј
    0.29
    Activations Density 0.023%

    No Known Activations