© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89076
    Prev
    Next
    INDEX
    Explanations

    information extraction and relation extraction

    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_11_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
    坨
    0.57
    nian
    0.52
    <0x0D>
    0.52
     carinatis
    0.51
    assment
    0.50
    卄
    0.50
     вакан
    0.50
    vskip
    0.49
    mila
    0.49
     Inspe
    0.49
    POSITIVE LOGITS
     andet
    0.52
    บ
    0.52
     b
    0.51
     možné
    0.49
    थे
    0.49
     army
    0.48
     colors
    0.46
     både
    0.46
     kunne
    0.46
     ol
    0.45
    Activations Density 0.041%

    No Known Activations