© 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. 161532
    Prev
    Next
    INDEX
    Explanations

    important de

    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
    >
    1.62
    il
    1.45
    u
    1.31
    (
    1.29
    에
    1.28
    ל
    1.27
    ר
    1.24
    s
    1.20
    ad
    1.17
    л
    1.08
    POSITIVE LOGITS
    lere
    1.15
    ंनी
    1.00
     інших
    0.96
     ovat
    0.95
     двох
    0.95
     août
    0.95
     εί
    0.94
     всі
    0.94
    ators
    0.93
    cussions
    0.93
    Activations Density 0.000%

    No Known Activations