© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5421
    Prev
    Next
    INDEX
    Explanations

    Okay, let's break down

    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
    وک
    1.26
    skih
    1.24
    م
    1.23
    रीत
    1.22
    ধার
    1.21
    nitz
    1.17
    larımız
    1.15
    ো
    1.15
    ەك
    1.14
    үкт
    1.14
    POSITIVE LOGITS
    ли
    1.66
    т
    1.43
     emperors
    1.34
    가
    1.32
    Список
    1.29
     inflammation
    1.29
     accords
    1.25
    া
    1.23
    inflammation
    1.20
    भ
    1.20
    Activations Density 0.136%

    No Known Activations