© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66836
    Prev
    Next
    INDEX
    Explanations

    voice

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    顼
    0.42
    wiring
    0.40
     nameof
    0.39
    WorkingDirectory
    0.38
     esters
    0.38
    nar
    0.38
     Nar
    0.37
    叙
    0.37
     NR
    0.36
     (_)
    0.36
    POSITIVE LOGITS
     voice
    2.19
     Voice
    1.95
    Voice
    1.95
    voice
    1.89
     VOICE
    1.68
     voce
    1.53
     voz
    1.52
    声
    1.51
     वॉइस
    1.50
     voix
    1.40
    Activations Density 0.003%

    No Known Activations