© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14235
    Prev
    Next
    INDEX
    Explanations

    concept of

    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_15_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
    CodeGen
    0.49
    OLIS
    0.48
    Price
    0.47
    toolStrip
    0.47
     Часто
    0.47
     경우가
    0.46
    i
    0.46
    ᅵ
    0.46
    𝐼
    0.46
    Pasta
    0.45
    POSITIVE LOGITS
    arsch
    0.46
    ée
    0.44
     финан
    0.43
     nella
    0.41
    uminate
    0.41
    舉辦
    0.41
     spiritually
    0.41
     vertically
    0.40
    iei
    0.40
     figlio
    0.40
    Activations Density 0.035%

    No Known Activations