© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120222
    Prev
    Next
    INDEX
    Explanations

    and

    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_27_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
     xứng
    0.40
    ccco
    0.40
    áló
    0.38
     mạnh
    0.38
     ক্ষতি
    0.37
     DAMAGES
    0.37
     Découvrez
    0.37
    昧
    0.37
    त्य
    0.37
     hồn
    0.37
    POSITIVE LOGITS
     polarization
    0.41
     sleeves
    0.41
     sometimes
    0.39
     mostly
    0.38
     transformation
    0.38
    utton
    0.38
    sometimes
    0.37
     நடத்திய
    0.36
    紫外線
    0.36
     sometime
    0.36
    Activations Density 0.027%

    No Known Activations