© 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. 2856
    Prev
    Next
    INDEX
    Explanations

    very specific

    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
     pues
    1.74
    로
    1.70
    iet
    1.64
    isering
    1.62
    <0x80>
    1.61
    ată
    1.59
    ah
    1.58
    دار
    1.58
    ıy
    1.57
    🏽
    1.54
    POSITIVE LOGITS
    ра
    2.20
    াল
    2.14
     worldly
    2.11
    ুঁ
    2.10
     walled
    1.98
    홧
    1.94
    ۰
    1.94
    minify
    1.90
     minifyEnabled
    1.89
     currentDate
    1.86
    Activations Density 0.053%

    No Known Activations