© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108298
    Prev
    Next
    INDEX
    Explanations

    gherkin syntax and keywords

    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_2_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
    in
    1.28
     be
    1.23
    you
    1.04
    你
    1.02
    be
    1.01
    van
    0.96
    met
    0.96
    IN
    0.95
    EN
    0.93
    pos
    0.93
    POSITIVE LOGITS
    :
    1.84
    る
    1.48
    ુ
    1.32
    ளை
    1.25
    と
    1.20
    ू
    1.14
    ா
    1.13
    ோ
    1.13
    ු
    1.13
    ים
    1.13
    Activations Density 0.000%

    No Known Activations