© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9434
    Prev
    Next
    INDEX
    Explanations

    stoicism

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     மாநில
    0.74
     manajemen
    0.72
     UCF
    0.69
    спа
    0.68
     एच
    0.68
    ชีพ
    0.68
    厉
    0.67
     Caball
    0.66
    Ꮋ
    0.66
    毕
    0.66
    POSITIVE LOGITS
     cell
    0.73
     ven
    0.67
     я
    0.65
     निजात
    0.64
     Cell
    0.63
    މ
    0.58
    Peng
    0.58
    '])->
    0.58
     ފ
    0.57
     jag
    0.57
    Activations Density 0.096%

    No Known Activations