© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123927
    Prev
    Next
    INDEX
    Explanations

    queens and icons

    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
     ratio
    0.40
     prostatitis
    0.40
     ratios
    0.39
     prostat
    0.38
     $<$
    0.38
     redis
    0.38
     contracting
    0.37
    manifold
    0.37
     mannit
    0.37
    >(
    0.36
    POSITIVE LOGITS
     queen
    0.71
     Queen
    0.67
     slay
    0.63
     queens
    0.59
    Queen
    0.59
     QUEEN
    0.59
    💅
    0.56
     ICON
    0.56
     gays
    0.55
     Icon
    0.54
    Activations Density 0.008%

    No Known Activations