© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80060
    Prev
    Next
    INDEX
    Explanations

    doble pár, details in

    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_0_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
     』
    0.55
     ទ
    0.52
     spazi
    0.50
     สะ
    0.49
     niemals
    0.49
     الكلام
    0.48
     பண்ப
    0.48
     ########
    0.47
     lokalen
    0.47
     setName
    0.47
    POSITIVE LOGITS
    For
    0.56
    ----------------
    0.55
     for
    0.52
    Es
    0.52
    e
    0.52
    for
    0.50
    Book
    0.49
    o
    0.49
    eros
    0.48
    print
    0.47
    Activations Density 0.000%

    No Known Activations