© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201502
    Prev
    Next
    INDEX
    Explanations

    9/11 memorial

    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_37_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
     달려
    0.40
    Pro
    0.40
     trei
    0.39
     xâm
    0.38
    딤
    0.37
    上限
    0.37
     urma
    0.36
    UpperBound
    0.35
    𝗟
    0.35
    нага
    0.35
    POSITIVE LOGITS
     cyclical
    0.41
     নেট
    0.39
    DateTimeField
    0.38
     ካ
    0.38
    掐
    0.38
    volt
    0.37
    足
    0.37
    胙
    0.37
     mind
    0.37
     comforting
    0.37
    Activations Density 0.001%

    No Known Activations