© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197884
    Prev
    Next
    INDEX
    Explanations

    places and geography

    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_50_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
     gp
    0.42
     হাসপাতালের
    0.39
    لع
    0.39
    
    0.39
    Birds
    0.38
     Sales
    0.38
     ն
    0.38
     gb
    0.38
     स्टो
    0.37
     pb
    0.36
    POSITIVE LOGITS
     rem
    0.43
    Rem
    0.43
     KW
    0.43
    deling
    0.43
     Imp
    0.43
     san
    0.41
    san
    0.41
    rem
    0.41
    redux
    0.41
     impar
    0.40
    Activations Density 0.000%

    No Known Activations