© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3492
    Prev
    Next
    INDEX
    Explanations

    react library names

    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_5_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
     расходов
    0.70
    spinner
    0.70
    のである
    0.67
    est
    0.67
    вести
    0.64
    экономи
    0.63
    '`--
    0.63
    anggap
    0.63
     permettant
    0.62
    als
    0.61
    POSITIVE LOGITS
    ுள்ள
    0.76
     legislation
    0.74
    lysis
    0.72
    legislation
    0.69
     striking
    0.68
    ƒ
    0.68
    ுள்ளார்
    0.64
     diterima
    0.64
    ுள்ளனர்
    0.63
    ❤❤
    0.62
    Activations Density 0.004%

    No Known Activations