© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7023
    Prev
    Next
    INDEX
    Explanations

    victory and triumph

    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_3_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
    holder
    3.30
    holders
    3.15
    taker
    3.13
     quarantined
    2.97
    手臂
    2.93
    $\$
    2.80
    toxicity
    2.76
     schizophrenia
    2.76
    en
    2.74
     effecting
    2.74
    POSITIVE LOGITS
     heed
    2.66
    वहीं
    2.53
    че
    2.43
     meisten
    2.43
    u
    2.42
     maja
    2.37
    েন্ট
    2.35
    ról
    2.34
     gesamten
    2.34
     часа
    2.33
    Activations Density 0.016%

    No Known Activations