© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126693
    Prev
    Next
    INDEX
    Explanations

    Boeing aircraft models

    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_37_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
     recombin
    0.42
     dishes
    0.41
     وعند
    0.39
     Hob
    0.38
     c
    0.37
     h
    0.37
     परिश
    0.37
     los
    0.36
     фла
    0.36
     Zu
    0.35
    POSITIVE LOGITS
    Road
    0.42
     রোড
    0.40
    发生在
    0.40
     சாலையில்
    0.40
    ROAD
    0.39
    陴
    0.38
    Witam
    0.38
     سپور
    0.38
     véhicule
    0.37
    Casey
    0.37
    Activations Density 0.000%

    No Known Activations