© 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. 3543
    Prev
    Next
    INDEX
    Explanations

    code comments or delimiters

    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
    ud
    0.65
    haven
    0.59
    é
    0.56
     exorbit
    0.56
    ülü
    0.56
    ä
    0.53
    études
    0.52
     està
    0.52
    限り
    0.52
     دې
    0.51
    POSITIVE LOGITS
    ‍♀️
    0.75
    ‍♂️
    0.71
    Snapped
    0.69
    ных
    0.66
    ️
    0.64
    ../../
    0.63
    ية
    0.63
    اً
    0.63
    い
    0.61
    ان
    0.61
    Activations Density 0.009%

    No Known Activations