© 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. 3450
    Prev
    Next
    INDEX
    Explanations

    sustain, livelihoods, self-sufficiency

    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
     haste
    1.44
     marred
    1.39
    不再
    1.37
    𝐞
    1.37
     convex
    1.33
     secuencia
    1.31
    天空
    1.30
    स्पद
    1.30
     patted
    1.29
    dır
    1.28
    POSITIVE LOGITS
    к
    1.03
    ১২
    1.02
    дя
    1.00
    ू
    0.99
     (\
    0.99
     Wage
    0.99
    Доб
    0.98
     Workforce
    0.95
    కుని
    0.95
    %(
    0.95
    Activations Density 0.077%

    No Known Activations