© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8446
    Prev
    Next
    INDEX
    Explanations

    instruments and vocals in the context of songs and bands

    oai_token-act-pair · gemini-2.0-flash

    guitar

    np_max-act · gemini-2.0-flash

    guitar

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     guitar
    -1.24
     guitarra
    -1.05
     guitars
    -1.03
     Guitar
    -1.00
     knife
    -1.00
    guitar
    -0.97
    Guitar
    -0.96
     Gitar
    -0.95
     Knife
    -0.92
     piano
    -0.89
    POSITIVE LOGITS
     typelib
    0.66
    <bos>
    0.60
    Sklici
    0.59
    }{*}{
    0.58
    LookAnd
    0.57
    nocache
    0.57
    QMetaType
    0.57
    uidado
    0.56
     initComponents
    0.56
     الحره
    0.56
    Activations Density 0.846%

    No Known Activations