© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36627
    Prev
    Next
    INDEX
    Explanations

    Automate the Boring Stuff with Python

    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
    s
    0.69
    e
    0.66
    f
    0.60
    szer
    0.59
    t
    0.59
    lado
    0.57
    sj
    0.57
    átu
    0.54
    xq
    0.53
    n
    0.53
    POSITIVE LOGITS
     exoskeleton
    0.57
    Lotus
    0.57
     noodles
    0.56
     throne
    0.55
     lotus
    0.55
    Referências
    0.54
    From
    0.54
    Productos
    0.54
     orchid
    0.54
     angios
    0.54
    Activations Density 0.001%

    No Known Activations