© 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. 6542
    Prev
    Next
    INDEX
    Explanations

    incoming communications, data, orders

    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
    िक
    1.06
     rgba
    1.00
    د
    0.85
    த்திர
    0.84
    ных
    0.81
    '.$
    0.81
    ం
    0.79
    𝙛
    0.78
    دق
    0.78
    टर
    0.78
    POSITIVE LOGITS
    S
    0.85
    Ngoài
    0.85
     windfall
    0.83
    পরে
    0.82
     vacancies
    0.80
     shortfall
    0.79
     найбіль
    0.79
    Portland
    0.78
     тобой
    0.78
     ingestion
    0.78
    Activations Density 0.002%

    No Known Activations