© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8282
    Prev
    Next
    INDEX
    Explanations

    Neptune

    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
    tei
    2.95
    o
    2.81
    ക്കാർ
    2.72
    れば
    2.70
    вий
    2.69
    स्पति
    2.66
    muestra
    2.60
    te
    2.59
    те
    2.56
    ен
    2.48
    POSITIVE LOGITS
    ът
    2.69
    ів
    2.68
    小
    2.59
    ইহ
    2.57
    б
    2.52
     morbidity
    2.48
    不然
    2.45
    NetAmount
    2.44
    ń
    2.42
    ಾಗಲೇ
    2.40
    Activations Density 0.012%

    No Known Activations