© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23645
    Prev
    Next
    INDEX
    Explanations

    <

    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_56_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
    ষ্ট্র
    0.42
    ..”
    0.38
     freedom
    0.38
     '">'
    0.38
     rése
    0.37
    告诉
    0.37
    ...]
    0.36
    
    0.36
     नॉर्थ
    0.35
     Cohn
    0.35
    POSITIVE LOGITS
     div
    0.64
    div
    0.61
     p
    0.48
     h
    0.46
     divs
    0.44
     img
    0.44
     diva
    0.42
     >
    0.41
     li
    0.39
     DIV
    0.38
    Activations Density 0.003%

    No Known Activations