© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206673
    Prev
    Next
    INDEX
    Explanations

    Breast

    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_46_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
     Mirror
    0.43
     දි
    0.42
     lantern
    0.40
    ⑩
    0.40
    ർഷ
    0.38
     H
    0.38
     lanterns
    0.38
    坸
    0.37
    hots
    0.37
    Mirror
    0.36
    POSITIVE LOGITS
     U
    0.59
    Breast
    0.57
     Tef
    0.54
    breast
    0.50
     tera
    0.49
     Breast
    0.49
    U
    0.48
     phyl
    0.47
     Rim
    0.47
    Rim
    0.47
    Activations Density 0.009%

    No Known Activations