© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 216503
    Prev
    Next
    INDEX
    Explanations

    numbers and counting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    ⣀
    0.28
     plainly
    0.25
    ")[
    0.25
    !!!!!!!!!!!!!!!!
    0.25
     overwhelmingly
    0.25
    <unused2197>
    0.25
    !!!"
    0.24
     outperformed
    0.24
    																						
    0.24
     developmentally
    0.24
    POSITIVE LOGITS
     উহার
    0.23
    lique
    0.22
    mer
    0.21
    omor
    0.21
    omorphic
    0.21
     mell
    0.21
     বিব
    0.21
    fluent
    0.20
    Ir
    0.20
    ar
    0.20
    Activations Density 0.000%

    No Known Activations