© 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. 143874
    Prev
    Next
    INDEX
    Explanations

    \frac{

    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
    на
    1.40
     for
    1.35
    ك
    1.30
    ين
    1.23
    ER
    1.16
     be
    1.12
    ナ
    1.02
    ור
    0.96
    ম
    0.95
    리
    0.94
    POSITIVE LOGITS
    ,
    1.23
    -
    1.09
    ’
    0.95
    ↵↵
    0.84
    '
    0.79
    ления
    0.74
    ledes
    0.70
    あり
    0.68
     intim
    0.68
    am
    0.66
    Activations Density 0.003%

    No Known Activations