© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 624
    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
    an
    1.08
    i
    0.94
    $-$
    0.93
    ंग
    0.92
    ${
    0.92
    ../
    0.91
     quotid
    0.89
    ῳ
    0.86
    ම්භ
    0.86
    ment
    0.86
    POSITIVE LOGITS
    انية
    1.10
    fini
    1.07
     aad
    1.02
     linal
    1.01
    nagyobb
    0.99
    änä
    0.98
     voluntarily
    0.97
    اني
    0.97
    stol
    0.96
     einzigen
    0.95
    Activations Density 0.036%

    No Known Activations