© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3225
    Prev
    Next
    INDEX
    Explanations

    but also

    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_5_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
    l
    2.32
    lL
    2.14
    س
    2.05
    nt
    1.78
    েই
    1.73
    然後
    1.71
    Absolutely
    1.63
    ことなく
    1.60
    最高の
    1.57
    ngen
    1.53
    POSITIVE LOGITS
    o
    2.09
    राबरी
    2.06
     nomencl
    2.00
    ه
    1.95
     submanifold
    1.88
     لحاظ
    1.84
     žel
    1.84
     liens
    1.83
     ciento
    1.83
     runoff
    1.83
    Activations Density 0.033%

    No Known Activations