© 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. 5151
    Prev
    Next
    INDEX
    Explanations

    meta- prefix

    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
    te
    3.11
    ׁ
    3.06
    𝖎
    2.90
    𝖑
    2.85
    ka
    2.85
    person
    2.65
    𝖊
    2.57
    forth
    2.55
    overset
    2.50
    kiewicz
    2.44
    POSITIVE LOGITS
    Longrightarrow
    2.71
    請
    2.62
    боли
    2.62
    る
    2.62
    eine
    2.58
     mayhem
    2.53
     vera
    2.49
     commas
    2.47
    Ꮫ
    2.44
     Bane
    2.42
    Activations Density 0.035%

    No Known Activations