© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 208701
    Prev
    Next
    INDEX
    Explanations

    programming, technical documentation, and code

    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_19_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
     J
    0.14
     made
    0.13
    ision
    0.13
    es
    0.13
    ...
    0.12
     three
    0.12
     interrupts
    0.12
     ice
    0.12
     HE
    0.12
    ish
    0.12
    POSITIVE LOGITS
    براير
    0.14
     Desenvolvimento
    0.13
    ϙ
    0.13
     Lippincott
    0.13
    㖘
    0.13
    ᇁ
    0.13
    \%)
    0.13
    ਤ
    0.13
     desenvolvimento
    0.12
     Pengembangan
    0.12
    Activations Density 0.001%

    No Known Activations