© 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. 171819
    Prev
    Next
    INDEX
    Explanations

    that you

    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
     pot
    0.32
    ㄉ
    0.31
     pouvez
    0.30
    paintbrush
    0.29
    ované
    0.29
     diperlukan
    0.29
     hairdryer
    0.28
     thorac
    0.28
     legislação
    0.28
     dünya
    0.27
    POSITIVE LOGITS
     οδηγ
    0.30
    캐
    0.29
     countered
    0.29
    reporting
    0.28
     BW
    0.27
     Ge
    0.27
    istemas
    0.26
     κάπο
    0.25
     ressort
    0.25
    毕业生
    0.25
    Activations Density 0.001%

    No Known Activations