© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150448
    Prev
    Next
    INDEX
    Explanations

    California

    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_60_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
     here
    0.41
     flying
    0.41
     main
    0.40
    最
    0.39
    主
    0.39
     bilateral
    0.38
     favored
    0.38
     flown
    0.38
     centered
    0.38
     crept
    0.38
    POSITIVE LOGITS
    –
    0.55
     –
    0.53
    $-$
    0.50
     $-$
    0.48
     –,
    0.47
     Davis
    0.46
     University
    0.45
     Boynton
    0.44
    (
    0.44
     dav
    0.43
    Activations Density 0.000%

    No Known Activations