© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170728
    Prev
    Next
    INDEX
    Explanations

    import statements

    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_20_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
     перево
    0.26
    γρά
    0.25
     WRITE
    0.25
    Æ
    0.24
    дям
    0.24
    ចេញ
    0.24
     बकरी
    0.24
     红
    0.24
    (=
    0.24
    DC
    0.24
    POSITIVE LOGITS
    ingresso
    0.28
    ದ
    0.28
     perturbations
    0.26
     endpoints
    0.25
    soluble
    0.25
     inp
    0.25
     cicat
    0.24
     दर्ज
    0.24
     ingresso
    0.24
    ाइंड
    0.24
    Activations Density 0.002%

    No Known Activations