© 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. 5281
    Prev
    Next
    INDEX
    Explanations

    just followed by a pause or elaboration

    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
    gown
    1.18
     Ciências
    1.12
    ত্ব
    1.10
     inhibitors
    1.08
     longiore
    1.07
    🩰
    1.06
    ivität
    1.04
    bewerken
    1.03
     вещи
    1.03
     Dekker
    1.02
    POSITIVE LOGITS
    er
    1.10
    ส์
    1.01
    att
    0.99
    so
    0.96
    v
    0.84
    াজ
    0.84
    ha
    0.84
    ার
    0.83
    ve
    0.81
    aka
    0.80
    Activations Density 0.026%

    No Known Activations