© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 8478
    Prev
    Next
    INDEX
    Explanations

    LEGO building and sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    y
    2.35
    л
    2.12
     austenite
    2.07
     mener
    2.04
    ে
    1.97
     hề
    1.90
    o
    1.86
     deter
    1.86
    sores
    1.85
     gwar
    1.83
    POSITIVE LOGITS
    ≌
    2.15
    ів
    2.06
    اردوشاعری
    2.04
    }}{\
    2.01
    clickHandler
    1.99
     resh
    1.96
    
    1.92
     sprouts
    1.91
    mnopqrst
    1.90
    suk
    1.90
    Activations Density 0.039%

    No Known Activations