© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169977
    Prev
    Next
    INDEX
    Explanations

    .</

    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
    ('>
    0.39
     )-
    0.39
    िजन
    0.35
    ->
    0.35
    Alder
    0.34
     ){
    0.34
    ('%
    0.33
    żeń
    0.33
    cue
    0.33
    িল
    0.33
    POSITIVE LOGITS
     Derechos
    0.40
     Skywalker
    0.37
     कोणी
    0.35
     Untitled
    0.35
     Manu
    0.35
    kBtu
    0.35
     concentrating
    0.34
    ":
    0.33
    "?>
    0.33
    禕
    0.33
    Activations Density 0.001%

    No Known Activations