© 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-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130778
    Prev
    Next
    INDEX
    Explanations

    "have" or "has" when followed by "got"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    O
    1.18
    ﺭ
    1.11
    IS
    1.05
    ায়
    0.99
    ר
    0.99
    は
    0.91
     glist
    0.90
    0.90
    ادي
    0.87
     opções
    0.86
    POSITIVE LOGITS
    h
    1.59
    ,
    1.17
    as
    1.15
    ast
    1.12
    an
    1.06
    og
    1.05
    in
    1.03
    ти
    1.03
    स
    1.03
    ul
    1.02
    Activations Density 0.001%

    No Known Activations