© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15152
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers related to music albums

    oai_token-act-pair · gemini-2.0-flash

    Musical albums

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ComVisible
    -0.63
    معلومات
    -0.61
     jScrollPane
    -0.58
     numberOfRows
    -0.58
     réduite
    -0.56
    IUrlHelper
    -0.56
     ddelweddau
    -0.55
    QMetaType
    -0.54
     informée
    -0.54
    hyrchwyd
    -0.53
    POSITIVE LOGITS
    AutoScaleMode
    0.57
     record
    0.55
     Vikipedi
    0.50
    rawDesc
    0.50
     flex
    0.50
    phous
    0.50
     defaultstate
    0.49
     proper
    0.48
     recorded
    0.47
    jsxFileName
    0.46
    Activations Density 1.217%

    No Known Activations