© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1436
    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
    न
    2.34
    signup
    2.32
    an
    2.21
    as
    2.16
    matig
    1.95
    ು
    1.94
    t
    1.92
    badlogic
    1.91
    sale
    1.88
    sman
    1.85
    POSITIVE LOGITS
     însă
    2.38
    ই
    1.89
    ಾಯಿ
    1.89
     પાસે
    1.88
    🅐
    1.87
    그런
    1.83
    爲
    1.82
     arbeid
    1.77
    আমার
    1.77
     thwart
    1.75
    Activations Density 0.155%

    No Known Activations