© 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. 2850
    Prev
    Next
    INDEX
    Explanations

    bad followed by negative noun

    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
    ${
    2.14
    textBox
    1.79
    $
    1.68
    $=
    1.63
    ogonal
    1.60
    azienda
    1.60
    JlcG
    1.59
     oblast
    1.59
    `${
    1.58
    𝐒
    1.56
    POSITIVE LOGITS
     खासा
    2.46
    р
    2.14
     buruk
    2.04
     bye
    1.95
    ría
    1.87
     알고
    1.82
     Samaritan
    1.82
    セイ
    1.81
     amminist
    1.81
    س
    1.81
    Activations Density 0.007%

    No Known Activations