© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236848
    Prev
    Next
    INDEX
    Explanations

    compressed air and pneumatic systems

    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_32_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
     رمز
    0.39
    符
    0.38
    quee
    0.37
    镜
    0.37
     Valves
    0.37
    Instr
    0.35
     విలువ
    0.34
    emin
    0.34
    符号
    0.34
    Compression
    0.34
    POSITIVE LOGITS
     প্লে
    0.48
     nettoyer
    0.44
     lote
    0.41
     anch
    0.40
    룰
    0.40
     convict
    0.39
     प्ले
    0.38
     Doherty
    0.38
     limpieza
    0.38
     limpi
    0.38
    Activations Density 0.002%

    No Known Activations