© 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. 5895
    Prev
    Next
    INDEX
    Explanations

    Shiva

    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
    re
    2.47
     ún
    2.39
     huh
    2.34
    ं
    2.24
     Ψ
    2.15
    cess
    2.13
     భాగంగా
    2.12
     inhal
    2.08
    ர்வு
    2.08
     delici
    2.07
    POSITIVE LOGITS
     perceive
    2.86
    ﺎ
    2.66
     pravo
    2.62
    ﺰ
    2.60
     subalgebra
    2.58
    iovascular
    2.51
    ﺔ
    2.50
     recyclerView
    2.45
     implying
    2.45
     myosin
    2.43
    Activations Density 0.007%

    No Known Activations