© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145345
    Prev
    Next
    INDEX
    Explanations

    images:

    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_0_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
    li
    1.89
    ו
    1.72
    le
    1.67
    ra
    1.56
    st
    1.52
    ла
    1.48
    ל
    1.45
    ,
    1.40
    ท
    1.37
     in
    1.34
    POSITIVE LOGITS
     résident
    1.41
     sufr
    1.27
    ви
    1.24
     añad
    1.24
     fréquentes
    1.21
     nettoy
    1.20
    returnValues
    1.20
    ুর
    1.19
     desvi
    1.19
     έχει
    1.18
    Activations Density 0.001%

    No Known Activations