© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7147
    Prev
    Next
    INDEX
    Explanations

    be + adjective/past participle

    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
     kunna
    2.28
     able
    2.26
    ﺩ
    2.10
     poder
    2.06
     siendo
    1.97
     kunne
    1.91
    𝐲
    1.78
    ির
    1.73
    咙
    1.71
    ्या
    1.71
    POSITIVE LOGITS
     כן
    1.97
     useNewUrlParser
    1.89
    н
    1.87
    ل
    1.82
     easily
    1.81
    он
    1.75
    Surname
    1.74
    لن
    1.74
    체의
    1.73
    탰
    1.71
    Activations Density 0.077%

    No Known Activations