© 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. 107589
    Prev
    Next
    INDEX
    Explanations

    archived

    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
    ↵
    1.16
    ার
    1.09
    -
    1.09
    ó
    1.04
    <0x80>
    1.02
    ER
    0.96
     çar
    0.96
     seçenek
    0.94
     zile
    0.93
    ير
    0.91
    POSITIVE LOGITS
    د
    1.38
    ка
    1.31
    c
    1.26
    d
    1.23
    ні
    1.16
    s
    1.16
     in
    1.15
    க்கு
    1.12
    ।
    1.09
    ។
    1.09
    Activations Density 0.000%

    No Known Activations