© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126297
    Prev
    Next
    INDEX
    Explanations

    height or dimension assignments

    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_37_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
    宽度
    1.00
     width
    0.90
    Width
    0.88
     Width
    0.86
     widths
    0.86
     шири
    0.86
    寬
    0.83
     ширина
    0.82
    宽
    0.79
    WIDTH
    0.78
    POSITIVE LOGITS
    setFixedHeight
    0.45
     groot
    0.39
     jh
    0.39
     rhyme
    0.38
    @{
    0.37
     Anna
    0.37
     Irene
    0.37
     Blackmore
    0.37
     tall
    0.37
     reh
    0.37
    Activations Density 0.004%

    No Known Activations