© 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. 36456
    Prev
    Next
    INDEX
    Explanations

    debatable

    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
    다
    0.64
    د
    0.63
    ן
    0.62
    al
    0.61
     κά
    0.58
     }}-
    0.57
    kadot
    0.57
     אל
    0.57
    ală
    0.56
    맨
    0.55
    POSITIVE LOGITS
    B
    0.77
    G
    0.63
     c
    0.63
    s
    0.63
     ihe
    0.62
     s
    0.61
    AT
    0.59
     speci
    0.59
    J
    0.59
    山本
    0.59
    Activations Density 0.001%

    No Known Activations