© 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. 40773
    Prev
    Next
    INDEX
    Explanations

    abstract art and concepts

    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
    ка
    0.78
    t
    0.64
    k
    0.60
    life
    0.59
    f
    0.57
    mayor
    0.54
    дона
    0.52
    kond
    0.52
    ली
    0.52
    kah
    0.51
    POSITIVE LOGITS
     技术
    0.61
    ’:
    0.59
     grado
    0.56
     பயிற்சிய
    0.55
     INCREASE
    0.55
     R
    0.55
     Example
    0.54
     设计
    0.54
    ’),
    0.54
     inexperienced
    0.54
    Activations Density 0.003%

    No Known Activations