© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162903
    Prev
    Next
    INDEX
    Explanations

    text-to-audio descriptions

    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_31_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
    语音
    0.65
    เสียง
    0.64
     vocal
    0.63
     accent
    0.62
     آواز
    0.62
     audio
    0.57
    Audio
    0.56
    声
    0.56
    音声
    0.55
     voice
    0.54
    POSITIVE LOGITS
     dehydration
    0.38
     bateria
    0.37
     METAL
    0.37
     metal
    0.37
     metadata
    0.37
    欄
    0.37
     ধাত
    0.37
     निप
    0.36
     निबंध
    0.36
     Parc
    0.36
    Activations Density 0.054%

    No Known Activations