© 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-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110830
    Prev
    Next
    INDEX
    Explanations

    expressing preference or choice

    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
     as
    1.36
    কে
    1.19
    '
    1.16
    ↵
    1.00
     pruž
    0.96
     resultado
    0.93
     antiguos
    0.89
    У
    0.88
     encargado
    0.86
     অন্তর্গত
    0.85
    POSITIVE LOGITS
    on
    1.42
    ח
    1.34
    ни
    1.33
    ק
    1.26
    am
    1.20
    ри
    1.19
    し
    1.17
    r
    1.13
    س
    1.12
    ิ
    1.12
    Activations Density 0.000%

    No Known Activations