© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52574
    Prev
    Next
    INDEX
    Explanations

    reduces load and risk

    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_30_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
     populous
    0.29
     twenty
    0.27
     alarming
    0.26
    improved
    0.25
    =[-
    0.25
    美丽
    0.25
     flawless
    0.25
     alcoholic
    0.24
     sprung
    0.24
     spring
    0.24
    POSITIVE LOGITS
     veya
    0.28
    Whether
    0.28
    Ή
    0.27
    甴
    0.27
     how
    0.27
    ではなく
    0.27
    But
    0.26
    TECH
    0.26
    仵
    0.26
    াতের
    0.25
    Activations Density 0.013%

    No Known Activations