© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42527
    Prev
    Next
    INDEX
    Explanations

    multiplication variables and formulas

    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_22_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
    ſe
    0.27
     ሁሉም
    0.26
     മല
    0.26
    анали
    0.25
    瞄
    0.25
    minute
    0.24
     tradeoff
    0.24
     இலங்க
    0.24
    мін
    0.24
    minas
    0.24
    POSITIVE LOGITS
     পারি
    0.23
     বিজে
    0.23
     isotype
    0.23
    路的
    0.23
    SdkVersion
    0.22
     Razer
    0.22
    䒾
    0.22
    㧡
    0.22
     attrs
    0.22
     পারত
    0.22
    Activations Density 0.029%

    No Known Activations