© 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. 3496
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "can"

    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
    uirre
    0.71
    Greet
    0.55
     "&#
    0.54
    nici
    0.54
     jums
    0.53
    Clinical
    0.52
     справ
    0.51
    udsman
    0.51
     отметить
    0.51
    yana
    0.51
    POSITIVE LOGITS
    ℍ
    0.62
     eigent
    0.58
     frameN
    0.56
     permission
    0.55
     nere
    0.54
    ীয়
    0.54
    are
    0.54
    ine
    0.53
    ️
    0.53
    ach
    0.52
    Activations Density 0.007%

    No Known Activations