© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2568
    Prev
    Next
    INDEX
    Explanations

    laid out groundwork

    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
    ⵕ
    0.20
     அண
    0.20
     diaphragm
    0.20
    शिप
    0.20
     overflows
    0.19
    ℕ
    0.19
     overflow
    0.19
    外国
    0.19
     Диа
    0.19
    兒
    0.19
    POSITIVE LOGITS
    ala
    0.21
    hee
    0.21
    ōs
    0.21
    Xs
    0.20
     Cere
    0.20
     bare
    0.20
     Pach
    0.20
    gem
    0.19
    sser
    0.19
    Express
    0.19
    Activations Density 0.035%

    No Known Activations