© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206573
    Prev
    Next
    INDEX
    Explanations

    what it means

    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_20_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
     nari
    0.27
     बोलो
    0.21
     Jawaharlal
    0.21
     обо
    0.21
     Xiu
    0.21
     exponents
    0.21
    ៈ
    0.20
    궜
    0.20
     Pune
    0.20
     ദേ
    0.20
    POSITIVE LOGITS
    meaning
    0.25
    szlig
    0.24
    <unused92>
    0.23
    Killer
    0.22
    ographic
    0.22
    killers
    0.22
    Ｐ
    0.22
     needs
    0.21
    Ether
    0.21
    Ν
    0.21
    Activations Density 0.030%

    No Known Activations