© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5307
    Prev
    Next
    INDEX
    Explanations

    bar over symbol

    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
    ный
    1.04
    Deviation
    1.03
    showMessage
    1.03
    니
    0.99
    يس
    0.98
    arı
    0.97
    اة
    0.97
    racht
    0.97
    ine
    0.95
    ہرست
    0.95
    POSITIVE LOGITS
     ולא
    1.14
    ل
    1.11
     incontr
    1.10
     contrairement
    1.07
    accharides
    1.06
     previsto
    1.04
    १
    1.04
    𝘳
    1.04
    এ
    1.04
     janeiro
    1.03
    Activations Density 0.001%

    No Known Activations