© 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. 2863
    Prev
    Next
    INDEX
    Explanations

    1970s old-school

    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
    pkl
    1.72
    lees
    1.71
     customtkinter
    1.70
    Архівовано
    1.66
    Ꮼ
    1.65
     spectrophot
    1.64
    д
    1.63
     crispy
    1.62
    getClassName
    1.58
    ে
    1.56
    POSITIVE LOGITS
     roku
    1.91
    ﻥ
    1.87
    까지
    1.83
    부터
    1.83
    ường
    1.82
    에
    1.82
    un
    1.72
     esté
    1.72
     fait
    1.70
    พาะ
    1.68
    Activations Density 0.012%

    No Known Activations