© 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. 13916
    Prev
    Next
    INDEX
    Explanations

    chess board notation

    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
     Concentration
    0.41
     Canvas
    0.38
    乾
    0.38
     Beaver
    0.37
    LLY
    0.37
     Kanji
    0.37
     Reconstruction
    0.37
     Blocking
    0.37
    yendo
    0.37
    ंबी
    0.37
    POSITIVE LOGITS
     tá
    0.39
     спо
    0.38
     лу
    0.38
    спо
    0.36
     DELHI
    0.35
    湘
    0.35
     அறி
    0.34
     кри
    0.34
     Nc
    0.33
     πά
    0.33
    Activations Density 0.014%

    No Known Activations