© 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. 5384
    Prev
    Next
    INDEX
    Explanations

    indirectly or indirect followed by a noun

    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
    м
    3.29
    不是很
    3.07
    ப்
    2.91
     pests
    2.88
    valueChanged
    2.88
    el
    2.85
    
    2.85
     været
    2.84
    𝗔
    2.77
    م
    2.73
    POSITIVE LOGITS
    у
    2.76
    oce
    2.38
    okban
    2.20
    мо
    2.15
    letzt
    2.14
     ""}
    2.12
    ீ
    2.11
    වා
    2.11
    ли
    2.11
     respecto
    2.10
    Activations Density 0.005%

    No Known Activations