© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3250
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    <0x80>
    2.10
     prue
    2.02
     logits
    2.01
     interesting
    1.96
    دود
    1.96
     Mutable
    1.93
    $_
    1.92
    artificial
    1.91
    ྀ
    1.91
    بق
    1.85
    POSITIVE LOGITS
    ர்
    2.37
    ה
    2.34
    и
    2.27
    ни
    2.12
     এজন্য
    2.11
    inin
    2.08
    ată
    2.04
    
    1.99
    ர்கள்
    1.93
    ется
    1.91
    Activations Density 0.077%

    No Known Activations