© 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. 489
    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
    ות
    2.42
    ীয়
    2.26
     trocar
    2.21
    स
    2.19
    ist
    2.19
    芃
    2.03
    деся
    2.00
    ła
    1.94
    ite
    1.89
    itions
    1.88
    POSITIVE LOGITS
    _-
    2.00
    ভাবে
    1.98
    ch
    1.93
    يء
    1.89
    ::-
    1.89
    notin
    1.88
     ppt
    1.88
     culmination
    1.86
    slope
    1.81
    ميل
    1.78
    Activations Density 0.165%

    No Known Activations