© 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. 3277
    Prev
    Next
    INDEX
    Explanations

    common word endings

    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
    లో
    1.17
    ಲ್ಲಿ
    1.08
    ╡
    1.02
     vỏ
    1.01
    स
    1.01
     lessened
    0.98
     retained
    0.97
    ক
    0.96
     σημ
    0.95
    withstanding
    0.94
    POSITIVE LOGITS
    ми
    1.32
    erçe
    1.16
    an
    1.06
    ли
    1.05
    elt
    1.05
    ast
    1.00
    ве
    0.99
     والك
    0.99
    ine
    0.99
    us
    0.99
    Activations Density 0.002%

    No Known Activations