© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133415
    Prev
    Next
    INDEX
    Explanations

    adjacency, adolescence

    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_1_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
    '
    1.98
    ла
    1.30
    นั้น
    1.13
    ด
    1.09
    \
    1.08
    ↵↵
    1.04
    त
    1.02
    ți
    1.00
    ↵
    0.99
    nya
    0.99
    POSITIVE LOGITS
     a
    1.26
     árv
    1.03
    ిల్
    0.98
     for
    0.98
    ine
    0.95
    ີ
    0.89
    э
    0.89
    瓈
    0.89
     வாழைப்பழம்
    0.88
    ెంట్
    0.87
    Activations Density 0.001%

    No Known Activations