© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7006
    Prev
    Next
    INDEX
    Explanations

    a mix of common English words like prepositions, articles, and conjunctions strung together

    oai_token-act-pair · gemini-2.0-flash

    snippets of extracted information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ReactDOM
    -0.63
     المعيارى
    -0.61
    makeConstraints
    -0.53
     XCTest
    -0.52
     AssemblyVersion
    -0.52
    NameInMap
    -0.52
    asticity
    -0.51
     onOptions
    -0.50
     LUMP
    -0.50
    URLException
    -0.49
    POSITIVE LOGITS
     and
    0.72
     kell
    0.54
     d
    0.53
    lagi
    0.51
     lagi
    0.50
     SEGU
    0.50
    maximum
    0.49
     sitting
    0.49
     sat
    0.48
     standing
    0.48
    Activations Density 0.396%

    No Known Activations