© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82856
    Prev
    Next
    INDEX
    Explanations

    bull bulldogs

    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_53_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
    
    0.39
    েত্রে
    0.38
    وض
    0.36
     lorf
    0.35
    Baxter
    0.34
    毡
    0.34
    ᴡ
    0.33
    
    0.33
     বাহ
    0.32
     joj
    0.32
    POSITIVE LOGITS
    Bul
    2.52
     Bul
    2.38
     bul
    2.33
    bul
    2.22
     BUL
    2.16
     Bull
    2.11
    BUL
    2.09
     bull
    2.08
    Bull
    2.08
     Bulldogs
    2.08
    Activations Density 0.017%

    No Known Activations