© 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. 253466
    Prev
    Next
    INDEX
    Explanations

    say "())"

    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
     ‘
    0.46
    :&
    0.42
    &
    0.42
    ͈
    0.40
     Ā
    0.40
     ʻ
    0.39
    )+'
    0.39
    ਸ਼ਨ
    0.39
    ֒
    0.39
    .&
    0.38
    POSITIVE LOGITS
    Shel
    0.38
    (){
    0.37
    crazy
    0.37
    #{
    0.36
    subject
    0.35
    hora
    0.35
    ()){
    0.34
     {#
    0.34
    scal
    0.34
    (#
    0.34
    Activations Density 0.001%

    No Known Activations