© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 12205
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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_13_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
     lensa
    0.20
     LIF
    0.19
     lifespan
    0.19
    Monter
    0.18
    唵
    0.18
     Surabaya
    0.18
     Sankt
    0.18
     Jacksonville
    0.18
     WebSocket
    0.18
    Jupiter
    0.18
    POSITIVE LOGITS
    agues
    0.18
     n
    0.17
    +
    0.17
    (?)
    0.17
    s
    0.17
     enacting
    0.15
    iro
    0.15
     +
    0.15
     unfortunate
    0.15
     camino
    0.15
    Activations Density 0.032%

    No Known Activations