© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11768
    Prev
    Next
    INDEX
    Explanations

    ("%d" format specifier)

    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_40_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
     нулю
    0.41
    零
    0.40
    drawer
    0.38
    thres
    0.37
    shiro
    0.36
     zero
    0.35
     Zero
    0.35
    zeros
    0.35
     डाल
    0.35
    籟
    0.35
    POSITIVE LOGITS
     Wikidata
    0.40
     PNG
    0.39
     defined
    0.39
     Bergh
    0.39
     NDP
    0.38
     攵
    0.38
     \}$
    0.37
    oga
    0.37
     പിന്നീട്
    0.37
     SOB
    0.36
    Activations Density 0.004%

    No Known Activations