© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4466
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to entertainment, performances, and media

    oai_token-act-pair · gemini-2.0-flash

    music

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ―――――
    -0.89
    UserScript
    -0.89
    tvguidetime
    -0.83
    ^(@)
    -0.82
     AssemblyCulture
    -0.82
    modelBuilder
    -0.82
     smtplib
    -0.81
    fattning
    -0.81
     createContext
    -0.79
    ✨:
    -0.78
    POSITIVE LOGITS
     music
    1.90
    music
    1.62
     Music
    1.55
    Music
    1.52
     MUSIC
    1.31
     Musik
    1.17
     muziek
    1.16
    MUSIC
    1.09
     musique
    1.08
     música
    1.05
    Activations Density 1.647%

    No Known Activations