© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27158
    Prev
    Next
    INDEX
    Explanations

    Pulse Width Modulation (PWM) signals waveforms

    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_10_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
    ও
    0.72
     uygulam
    0.71
     Ekim
    0.71
     konum
    0.69
    October
    0.69
    Alaska
    0.68
     hearers
    0.68
    ל
    0.68
    ")
    0.67
     ç
    0.66
    POSITIVE LOGITS
    㶲
    0.72
    og
    0.59
    ные
    0.59
    or
    0.57
    ogenerated
    0.57
    傆
    0.57
    涝
    0.57
    ιδ
    0.56
    ιουργ
    0.55
    efeu
    0.55
    Activations Density 0.015%

    No Known Activations