© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64515
    Prev
    Next
    INDEX
    Explanations

    vocal

    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
    voice
    0.68
    Voice
    0.67
     Voice
    0.64
     voice
    0.59
    Sound
    0.59
    声
    0.57
     आवाज
    0.56
     صوت
    0.55
     voz
    0.54
     sound
    0.52
    POSITIVE LOGITS
     nbfs
    0.44
     catchy
    0.42
     memoranda
    0.39
    簹
    0.39
    peers
    0.39
    ാവ
    0.38
     ferv
    0.38
     ble
    0.38
     innocuous
    0.38
     excit
    0.38
    Activations Density 0.002%

    No Known Activations