© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136478
    Prev
    Next
    INDEX
    Explanations

    degrees earned or held

    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
    棈
    0.54
     surgically
    0.43
     Menlo
    0.37
    \},\
    0.35
     levers
    0.35
    LoginPage
    0.34
     buckles
    0.34
    邯
    0.34
    elijk
    0.34
    gages
    0.34
    POSITIVE LOGITS
     Ambul
    0.41
     निभाने
    0.40
     поку
    0.40
    hyst
    0.39
    bapt
    0.37
    /∂
    0.36
     settlor
    0.36
     नारायण
    0.36
    ieß
    0.35
     ısı
    0.35
    Activations Density 0.001%

    No Known Activations