© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53598
    Prev
    Next
    INDEX
    Explanations

    conditional checks like if column >

    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_30_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
     ци
    0.37
     Victims
    0.36
     當
    0.35
    表示
    0.32
     chemically
    0.32
     ব্রিটিশ
    0.32
    ELINE
    0.32
    떴
    0.32
     شیمی
    0.31
     ;{
    0.31
    POSITIVE LOGITS
    function
    0.36
    egal
    0.34
    ToBounds
    0.34
    if
    0.33
    فيد
    0.32
     prefer
    0.32
     mejor
    0.32
     extrad
    0.31
    gever
    0.31
    iedad
    0.31
    Activations Density 0.002%

    No Known Activations