© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20664
    Prev
    Next
    INDEX
    Explanations

    opening delimiters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    `${
    0.45
    \}_{
    0.41
     boom
    0.38
    =$(
    0.38
     `./
    0.38
     کړئ
    0.37
    `(
    0.36
    दिग्ध
    0.35
     چک
    0.35
    )}(
    0.35
    POSITIVE LOGITS
     (“
    2.23
     ("
    2.13
     (‘
    2.06
     ('
    2.05
     ["
    1.90
    (“
    1.87
     («
    1.80
     („
    1.79
    ["
    1.77
     ['
    1.76
    Activations Density 0.190%

    No Known Activations