© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14403
    Prev
    Next
    INDEX
    Explanations

    grass-fed

    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_13_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
     प्रेम
    0.50
     c
    0.50
    प्रेम
    0.47
    s
    0.46
     L
    0.45
     हॉल
    0.44
     conform
    0.42
     суть
    0.42
     bouts
    0.41
     दुरु
    0.41
    POSITIVE LOGITS
    жета
    0.44
    輳
    0.44
    endorong
    0.43
    ٨
    0.42
    ()))
    0.41
    ९
    0.41
    romagnetic
    0.41
     meie
    0.41
     Schmitz
    0.40
    兒童
    0.40
    Activations Density 0.027%

    No Known Activations