© 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. 5187
    Prev
    Next
    INDEX
    Explanations

    words ending in 've' or 're'

    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
    ت
    0.99
    ി
    0.87
    تان
    0.83
    т
    0.82
    れ
    0.80
     addicted
    0.80
     perone
    0.80
    jších
    0.79
    ிருந்தது
    0.76
    عرف
    0.73
    POSITIVE LOGITS
    𝐯
    0.98
    िक
    0.90
    ...+
    0.88
    𝐝
    0.87
    𝐡
    0.86
     поги
    0.81
    𝐫
    0.81
    ५
    0.80
     kori
    0.79
    𝐄
    0.78
    Activations Density 0.190%

    No Known Activations