© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 6904
    Prev
    Next
    INDEX
    Explanations

    remove dirt and residue

    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_40_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
     забруд
    0.32
     fouling
    0.31
    污染
    0.31
     stain
    0.30
     Fatigue
    0.30
     deformation
    0.30
     fouled
    0.30
    汚
    0.30
     dirty
    0.29
     smelly
    0.29
    POSITIVE LOGITS
     meat
    0.25
    printDialog
    0.24
    pric
    0.24
    肉
    0.24
    㱛
    0.24
    SAN
    0.24
    CHUNK
    0.23
    饭
    0.23
    meat
    0.23
    BOUND
    0.23
    Activations Density 0.089%

    No Known Activations