© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4503
    Prev
    Next
    INDEX
    Explanations

    the prefix "Mus"

    oai_token-act-pair · gemini-2.0-flash

    tokens related to music

    np_token-act-pair-logits · gpt-4o-mini

    Mus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    inaison
    -0.87
    
    -0.81
    RegistryLite
    -0.81
    InjectAttribute
    -0.80
     <>",
    -0.79
     kasarigan
    -0.78
    BufferException
    -0.78
    ExtendWith
    -0.77
    KommentareTeilen
    -0.75
    VersionUID
    -0.75
    POSITIVE LOGITS
    tan
    0.42
    وق
    0.39
     taches
    0.37
    ...
    0.37
     Lindberg
    0.36
     touched
    0.36
    oling
    0.36
    …
    0.35
    <bos>
    0.35
    tell
    0.35
    Activations Density 0.297%

    No Known Activations