© 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-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14617
    Prev
    Next
    INDEX
    Explanations

    terms related to music, instruments, and opera

    oai_token-act-pair · gemini-2.0-flash

    singing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     useAppContext
    -0.52
    HostException
    -0.51
    queryInterface
    -0.50
    OwnProperty
    -0.47
    hashtags
    -0.47
    '}>
    -0.46
     makeStyles
    -0.46
    rigs
    -0.46
    ]}>
    -0.46
     везе
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.85
     Gesang
    0.73
     Singing
    0.68
     singing
    0.66
     <>",
    0.65
    المناصب
    0.63
     singers
    0.63
     voice
    0.62
     Voice
    0.61
     Vocals
    0.60
    Activations Density 0.739%

    No Known Activations