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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3012
    Prev
    Next
    INDEX
    Explanations

    partial derivative symbols

    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
    عل
    0.78
    न
    0.73
    מו
    0.73
    ране
    0.71
    ش
    0.70
    tip
    0.66
    പ്പാ
    0.66
    𝙜
    0.66
     Tage
    0.65
    กลาง
    0.65
    POSITIVE LOGITS
     ascends
    0.97
    al
    0.84
     cannabinoids
    0.82
     asserts
    0.82
    啶
    0.80
     sanctity
    0.80
     yen
    0.80
     abr
    0.79
     austerity
    0.78
    BJP
    0.77
    Activations Density 0.003%

    No Known Activations