© 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. 15977
    Prev
    Next
    INDEX
    Explanations

    mentions of band or performer names, recording labels, or popular songs in the context of a band's history.

    oai_token-act-pair · gemini-2.0-flash

    Musical artists and music

    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
    ёх
    -0.55
    MessageOf
    -0.52
     wikihow
    -0.51
     ***!
    -0.50
    ="@+
    -0.50
    AnimationsModule
    -0.50
    featureID
    -0.50
     AssemblyProduct
    -0.50
    saraba
    -0.49
    GraphicsUnit
    -0.48
    POSITIVE LOGITS
     OFDb
    0.60
     XCTest
    0.58
    CppMethod
    0.55
    انيف
    0.55
     Temptation
    0.54
     يول
    0.53
    WebVitals
    0.49
    ombie
    0.49
     Dynamite
    0.49
     Furious
    0.49
    Activations Density 6.445%

    No Known Activations