© 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. 2836
    Prev
    Next
    INDEX
    Explanations

    form html structure

    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
    ষুধ
    0.45
    м
    0.41
    的には
    0.40
     deu
    0.39
    ่ง
    0.37
    ppen
    0.36
     emotion
    0.36
    లువ
    0.35
     Accesat
    0.35
     halinde
    0.35
    POSITIVE LOGITS
    th
    0.41
    تال
    0.40
    能
    0.40
    ు
    0.39
    스러운
    0.39
    屜
    0.38
    ería
    0.38
    aient
    0.38
    as
    0.37
    스럽
    0.37
    Activations Density 0.003%

    No Known Activations