© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164048
    Prev
    Next
    INDEX
    Explanations

    cybernetic enhancements and augmentation

    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_31_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
     hashing
    0.36
    arabangsa
    0.35
     climbing
    0.33
     thoại
    0.31
    ች
    0.31
     hash
    0.31
    hash
    0.31
     sending
    0.31
     Sending
    0.31
     embedding
    0.30
    POSITIVE LOGITS
     biosynthetic
    0.33
     rendszer
    0.32
     maquinaria
    0.31
     instalado
    0.31
    っこ
    0.31
     সৌর
    0.31
     erythemat
    0.30
    >`;
    0.29
    怅
    0.29
     watercolors
    0.29
    Activations Density 0.014%

    No Known Activations