© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196281
    Prev
    Next
    INDEX
    Explanations

    jade sculptures and jewelry

    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
    Blurred
    0.57
    鄞
    0.53
     ImageTk
    0.52
    坆
    0.52
     للمع
    0.52
     المط
    0.50
    textepsilon
    0.50
    𝙊
    0.50
    愘
    0.50
    спект
    0.50
    POSITIVE LOGITS
     or
    0.73
     =
    0.66
    iri
    0.59
     या
    0.57
     Son
    0.57
    ica
    0.56
    son
    0.55
     Texas
    0.55
     Florida
    0.55
     This
    0.54
    Activations Density 0.000%

    No Known Activations