© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44684
    Prev
    Next
    INDEX
    Explanations

    Buckingham Palace changing of the guard

    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_13_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
    ździer
    0.51
    yczne
    0.48
    parvec
    0.47
    bedingungen
    0.47
    elwv
    0.47
    {
    0.47
    ˶
    0.46
    ফার
    0.46
     Emiliano
    0.46
    cccnc
    0.46
    POSITIVE LOGITS
     (
    0.58
    P
    0.58
     P
    0.50
     la
    0.47
     J
    0.47
       
    0.46
     Able
    0.45
     remembrance
    0.45
     описа
    0.45
     הפ
    0.44
    Activations Density 0.015%

    No Known Activations