© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12541
    Prev
    Next
    INDEX
    Explanations

    WAV files and audio recordings

    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_13_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
    нус
    0.45
     verdes
    0.45
     stabilité
    0.45
     stability
    0.44
    ق
    0.44
     solidity
    0.42
     scarce
    0.42
    ρίας
    0.42
     fibrous
    0.41
     functionalities
    0.41
    POSITIVE LOGITS
    köy
    0.54
     зву
    0.52
    音频
    0.49
     dźwię
    0.48
    音
    0.47
    🔉
    0.47
    サウンド
    0.45
    \":\"
    0.44
     음악
    0.44
     音
    0.43
    Activations Density 0.068%

    No Known Activations