© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5137
    Prev
    Next
    INDEX
    Explanations

    activation function

    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_3_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
     medida
    1.16
    nosi
    1.09
    ுள்ளார்
    1.09
    ä
    1.05
    or
    1.03
    스러
    1.03
    нное
    1.00
    ि
    0.98
    нные
    0.98
    ときの
    0.97
    POSITIVE LOGITS
    人
    1.29
    ರಿದ
    1.26
    theless
    1.24
    cough
    1.23
    quarters
    1.23
    ்களின்
    1.22
    comings
    1.18
    तौर
    1.16
    cstdlib
    1.14
    Grocery
    1.13
    Activations Density 0.004%

    No Known Activations