© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8680
    Prev
    Next
    INDEX
    Explanations

    year of

    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
     microscope
    2.89
    
    2.85
    臾
    2.84
    ście
    2.66
    
    2.64
    
    2.54
    
    2.53
    opposite
    2.51
    ﺎ
    2.50
     synergies
    2.44
    POSITIVE LOGITS
    lings
    2.21
    uct
    2.20
    zeiten
    2.14
    روز
    2.14
    நாடு
    2.12
    يمه
    2.04
    at
    2.00
    ि
    2.00
    rl
    1.99
    夏天
    1.99
    Activations Density 0.042%

    No Known Activations