© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173416
    Prev
    Next
    INDEX
    Explanations

    shows some quality

    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
     ነገር
    0.44
     አበባ
    0.44
     Crore
    0.43
     набира
    0.43
     블
    0.42
    يير
    0.42
    WithSize
    0.41
     සහිත
    0.41
    墘
    0.41
     मद्देन
    0.40
    POSITIVE LOGITS
    ünsche
    0.48
    linearity
    0.44
    பே
    0.42
    oneg
    0.41
     Jumat
    0.41
    auté
    0.40
    \}
    0.40
     Lemmas
    0.40
     शुक्रवार
    0.39
     शुभकामनाएं
    0.39
    Activations Density 0.028%

    No Known Activations