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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8159
    Prev
    Next
    INDEX
    Explanations

    "First things first" idiom

    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
    掍
    2.77
    TextViewStyle
    2.50
    /−
    2.39
    т
    2.35
     wits
    2.31
    i
    2.31
     regressions
    2.30
     hitter
    2.29
     Deutsche
    2.27
    掑
    2.25
    POSITIVE LOGITS
    𝐝
    2.86
    𝐤
    2.75
    น่า
    2.63
    𝐭
    2.55
    𝐢
    2.50
    Acetic
    2.49
    ية
    2.49
    -\
    2.47
    𝐚
    2.45
    𝐦
    2.45
    Activations Density 0.001%

    No Known Activations