© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260300
    Prev
    Next
    INDEX
    Explanations

    like it did

    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_10_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
    必
    0.39
     sebelumnya
    0.38
    ya
    0.35
    茄
    0.35
     any
    0.35
     before
    0.34
    ’,
    0.33
     serves
    0.33
    昨日
    0.33
    thys
    0.33
    POSITIVE LOGITS
     disposição
    0.46
    Чтобы
    0.41
     Secretario
    0.41
    藠
    0.40
    ո
    0.39
    еди
    0.39
    Hydrochloride
    0.39
    ucionales
    0.39
     نبی
    0.38
    ֽ
    0.38
    Activations Density 0.001%

    No Known Activations