© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3033
    Prev
    Next
    INDEX
    Explanations

    words about music, songs, albums, and playing them

    oai_token-act-pair · gemini-2.0-flash

    music context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     track
    -0.85
    track
    -0.66
     Track
    -0.61
     song
    -0.59
    song
    -0.56
    BrowserModule
    -0.55
    BagConstraints
    -0.51
    등학교
    -0.50
     single
    -0.50
    Track
    -0.49
    POSITIVE LOGITS
     calendriers
    0.60
    ؤلاء
    0.57
     eventdata
    0.52
    ReadInt
    0.48
     Feier
    0.48
    zwald
    0.47
    hadoop
    0.47
     AssemblyCompany
    0.47
    WillAppear
    0.46
    éraux
    0.46
    Activations Density 3.077%

    No Known Activations