© 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. 3050
    Prev
    Next
    INDEX
    Explanations

    Controller, setTimeout

    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
    ل
    0.44
    м
    0.44
    徳
    0.43
     maat
    0.43
    〢
    0.42
     kader
    0.42
    er
    0.42
    ι
    0.42
     ähm
    0.42
     प्रति
    0.42
    POSITIVE LOGITS
    possibly
    0.42
     UserService
    0.41
    ernetes
    0.41
     ISNI
    0.39
    minded
    0.39
     flavored
    0.39
    }")
    0.39
     Jir
    0.39
    机关
    0.38
    sonian
    0.38
    Activations Density 0.003%

    No Known Activations