© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46146
    Prev
    Next
    INDEX
    Explanations

    let's build/create something

    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_22_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
    avorable
    0.26
    陲
    0.25
     slowly
    0.24
     megh
    0.23
    glied
    0.23
    huge
    0.23
    avari
    0.22
    ✲
    0.22
     nearly
    0.22
     informally
    0.22
    POSITIVE LOGITS
     मक्
    0.26
     édition
    0.26
     spettacolo
    0.26
    CEPTION
    0.25
     स्टाइलिश
    0.25
    ЕН
    0.25
    Ку
    0.25
     Tasting
    0.25
     owners
    0.24
     Ensure
    0.24
    Activations Density 0.005%

    No Known Activations