© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15152
    Prev
    Next
    INDEX
    Explanations

    4G, 5G

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    사
    0.51
    𝒶
    0.50
    єкт
    0.49
    全
    0.48
    מו
    0.47
    시
    0.47
    काब
    0.46
    Checkbox
    0.46
     теста
    0.46
    Ка
    0.46
    POSITIVE LOGITS
     Peach
    0.49
     Peachtree
    0.48
     cure
    0.47
     Portland
    0.44
     Когда
    0.44
     wild
    0.43
    ].
    0.43
    </h6>
    0.42
     Precision
    0.42
    edge
    0.42
    Activations Density 0.011%

    No Known Activations