© 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. 16494
    Prev
    Next
    INDEX
    Explanations

    apache config & log

    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
     salinity
    0.44
     crab
    0.41
    '])){
    0.41
     زائ
    0.41
     hermit
    0.40
     Crab
    0.40
     Cr
    0.39
    ')){
    0.38
    蟹
    0.38
     crabs
    0.38
    POSITIVE LOGITS
     vent
    0.38
    木
    0.38
    vent
    0.38
     Conform
    0.38
    䔬
    0.37
     Gui
    0.36
    omás
    0.36
    釹
    0.35
     لال
    0.35
     Forward
    0.35
    Activations Density 0.024%

    No Known Activations