© 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. 3497
    Prev
    Next
    INDEX
    Explanations

    costly expenditure

    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
    楪
    0.47
    ت
    0.43
    
    0.43
    เภท
    0.41
    wanie
    0.41
    teen
    0.41
    adidas
    0.41
    JU
    0.41
    achievement
    0.40
    orifice
    0.40
    POSITIVE LOGITS
    देश
    0.50
     gus
    0.47
     coût
    0.47
     incurred
    0.44
     multilingual
    0.44
    ﴿
    0.44
     (>
    0.42
    ór
    0.42
     مرم
    0.41
     homozyg
    0.41
    Activations Density 0.258%

    No Known Activations