© 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. 40242
    Prev
    Next
    INDEX
    Explanations

    a prototypeprototype ofprototype for

    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
     ornith
    0.59
     curtailed
    0.59
     hipótes
    0.57
     principio
    0.55
    ൺ
    0.54
     criou
    0.54
     cor
    0.50
     retrato
    0.50
     aument
    0.50
     patrimonio
    0.50
    POSITIVE LOGITS
    d
    0.70
    x
    0.64
    das
    0.64
    p
    0.61
    .。
    0.60
    ти
    0.59
    .
    0.58
    k
    0.58
    dS
    0.58
    9
    0.57
    Activations Density 0.003%

    No Known Activations