© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13031
    Prev
    Next
    INDEX
    Explanations

    mentions of verses in a song as well as song components like a bridge or verse

    oai_token-act-pair · gemini-2.0-flash

    Chorus or bridge

    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
    IntoConstraints
    -0.87
    ագրություններ
    -0.74
    GraphicsUnit
    -0.70
    dafx
    -0.69
    Hentet
    -0.67
    tvguidetime
    -0.65
    enschappelijke
    -0.63
     BoxFit
    -0.63
    ThroughAttribute
    -0.62
    NameInMap
    -0.62
    POSITIVE LOGITS
     bridge
    1.05
     BRIDGE
    0.88
    bridge
    0.86
     Bridge
    0.83
    Bridge
    0.82
     bridges
    0.73
     chorus
    0.73
    BRIDGE
    0.73
    桥
    0.60
    brücke
    0.56
    Activations Density 1.266%

    No Known Activations