© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 726
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    $('#
    0.45
    _+
    0.45
    луйста
    0.44
    ²
    0.44
     과
    0.44
    redir
    0.43
     utterances
    0.42
     하
    0.42
    А
    0.42
     oscillation
    0.41
    POSITIVE LOGITS
    ﺮ
    0.51
    ﻪ
    0.49
    ﺎ
    0.45
    ر
    0.44
    առ
    0.42
    ো
    0.42
    ர்
    0.42
    ヤー
    0.42
     quale
    0.41
    inės
    0.41
    Activations Density 0.810%

    No Known Activations