© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5861
    Prev
    Next
    INDEX
    Explanations

    API CLIENT secret command ftp AWS OPEN

    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_3_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
    prev
    1.58
    可以
    1.42
    রকম
    1.40
    𝔱
    1.40
    𝑖
    1.39
     başında
    1.38
     पटा
    1.37
    webkit
    1.37
    ال
    1.37
    😂😂
    1.35
    POSITIVE LOGITS
     own
    1.99
     Own
    1.91
     عمل
    1.78
     jaoks
    1.65
     enig
    1.60
    اید
    1.52
    inios
    1.51
    qquad
    1.51
    ീ
    1.48
     GameObject
    1.47
    Activations Density 0.053%

    No Known Activations