© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3723
    Prev
    Next
    INDEX
    Explanations

    regardless of

    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
    𝑛
    1.28
    ক
    1.21
     rapt
    1.14
    ्
    1.14
    िक
    1.13
    érapie
    1.11
    ع
    1.10
    𝑠
    1.08
    nlü
    1.07
    ك
    1.06
    POSITIVE LOGITS
     warranties
    1.26
     precluded
    1.26
     crou
    1.21
     DWI
    1.20
     empê
    1.15
     betrayed
    1.15
    lni
    1.14
     perturbed
    1.14
    খেজুর
    1.11
     wary
    1.09
    Activations Density 0.003%

    No Known Activations