© 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. 8571
    Prev
    Next
    INDEX
    Explanations

    Kraftwerk, Powerlessness, government, Force

    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
     fossils
    2.37
    phi
    2.29
     noteworthy
    2.25
    もっと
    2.20
     crumbs
    2.20
    Switzerland
    2.18
     recourse
    2.18
    ④
    2.17
     faucets
    2.16
     реки
    2.16
    POSITIVE LOGITS
    勹
    3.53
    犸
    2.99
     тока
    2.39
     lượng
    2.36
     majeure
    2.32
    lifting
    2.26
    వంత
    2.25
    烈的
    2.21
     vives
    2.20
    வாய்
    2.17
    Activations Density 0.135%

    No Known Activations