© 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. 211613
    Prev
    Next
    INDEX
    Explanations

    learning variations/difficulties

    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
    ']:
    0.44
    searchText
    0.40
    狀況
    0.40
    ოში
    0.40
    ဟ
    0.40
    WEST
    0.39
    が大
    0.38
     Economy
    0.38
    զ
    0.38
    ropathy
    0.38
    POSITIVE LOGITS
     called
    0.45
     simplices
    0.44
    uições
    0.43
     continua
    0.43
    Fav
    0.42
    तियों
    0.42
     hatched
    0.42
     solidified
    0.41
    dures
    0.41
    بع
    0.41
    Activations Density 0.001%

    No Known Activations