© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7253
    Prev
    Next
    INDEX
    Explanations

    the names of musical instruments and also seems to be associated with formal funding acknowledgement

    oai_token-act-pair · gemini-2.0-flash

    terms related to musical instruments or components

    np_token-act-pair-logits · gpt-4o-mini
    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
    DoubleQuotes
    -0.74
    ViewImports
    -0.73
     esternos
    -0.70
     للمعارف
    -0.63
     mourut
    -0.61
    ۜ
    -0.61
     enfans
    -0.60
     empirically
    -0.60
    Diwedd
    -0.59
     SIAM
    -0.58
    POSITIVE LOGITS
     ब्रेकडाउन
    0.60
    曖昧さ回避
    0.48
     simplifié
    0.48
    transQ
    0.47
    __':
    0.46
     Seeder
    0.43
     Ed
    0.43
    oplayer
    0.42
    RRect
    0.41
    __':
    0.40
    Activations Density 0.256%

    No Known Activations