© 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. 137676
    Prev
    Next
    INDEX
    Explanations

    ifdef

    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
     broken
    0.42
     %(
    0.41
    Broken
    0.41
     há
    0.40
     Broken
    0.39
     übrig
    0.39
     waist
    0.38
    ✕
    0.37
     Waist
    0.37
    ∅
    0.37
    POSITIVE LOGITS
    alto
    0.41
     Berge
    0.39
    အောင်
    0.38
    arsipkan
    0.38
     လုပ်
    0.38
     Leicester
    0.37
     valentines
    0.37
    तांत्रिक
    0.37
     antérieurs
    0.37
    ቃት
    0.37
    Activations Density 0.000%

    No Known Activations