© 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. 245811
    Prev
    Next
    INDEX
    Explanations

    starlette

    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
     এমনি
    0.40
     מש
    0.39
     মেট্র
    0.38
    舴
    0.38
     Hatch
    0.38
     müş
    0.38
     upwards
    0.37
    䨋
    0.37
     Hash
    0.36
    স
    0.36
    POSITIVE LOGITS
    HANG
    0.42
     lig
    0.40
    ₁,
    0.39
    rames
    0.38
     liger
    0.38
    йы
    0.37
     ডিজাইন
    0.37
    MB
    0.37
    ctype
    0.37
    ₁)
    0.36
    Activations Density 0.002%

    No Known Activations