© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1278
    Prev
    Next
    INDEX
    Explanations

    audio processing code

    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
    ClientRect
    0.43
    pike
    0.40
    顺
    0.39
    順
    0.38
     বয়
    0.37
    वाया
    0.37
    స్తాయి
    0.37
     আঘাতে
    0.37
    願意
    0.37
    velocityX
    0.36
    POSITIVE LOGITS
     audio
    0.95
     Audio
    0.88
    Audio
    0.85
     音
    0.84
    audio
    0.80
    音频
    0.80
     speech
    0.79
    音
    0.77
     аудио
    0.77
     sound
    0.76
    Activations Density 0.041%

    No Known Activations