© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33084
    Prev
    Next
    INDEX
    Explanations

    square feet

    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_40_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
     vở
    0.38
     Merkel
    0.37
    場所に
    0.37
    륜
    0.37
     kilograms
    0.36
    frameN
    0.35
    мере
    0.35
     My
    0.34
     stro
    0.34
     Dust
    0.34
    POSITIVE LOGITS
    objective
    0.36
     ço
    0.36
    が大きい
    0.36
     scelte
    0.36
    iforme
    0.35
    ស្ន
    0.35
     bội
    0.34
     sconf
    0.34
     b
    0.34
     spit
    0.34
    Activations Density 0.002%

    No Known Activations