© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92738
    Prev
    Next
    INDEX
    Explanations

    Ola/Uber, auto-rickshaws

    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_11_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
     September
    0.50
     D
    0.49
    í
    0.47
    u
    0.46
    ia
    0.45
    yl
    0.45
     october
    0.45
    ou
    0.45
    \
    0.45
    spieler
    0.44
    POSITIVE LOGITS
     تؤ
    0.57
     أعمال
    0.57
    挝
    0.55
     будут
    0.54
    LETIN
    0.51
     изу
    0.51
     зре
    0.50
     اف
    0.50
     violación
    0.50
     confertim
    0.50
    Activations Density 0.000%

    No Known Activations