© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49586
    Prev
    Next
    INDEX
    Explanations

    Gemma

    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_31_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
    Clear
    0.36
    ্যন্তরীণ
    0.36
     Metabol
    0.34
     Jwt
    0.33
    Coastal
    0.33
    
    0.33
    autes
    0.33
    Traits
    0.33
    Ň
    0.33
    Png
    0.32
    POSITIVE LOGITS
    你是
    0.36
     මහ
    0.34
     curling
    0.33
     según
    0.32
    روز
    0.32
     menurut
    0.32
     ಎಂದು
    0.31
     होऊ
    0.31
    ాయని
    0.31
    ड़ने
    0.31
    Activations Density 0.005%

    No Known Activations