© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8422
    Prev
    Next
    INDEX
    Explanations

    interview Q&A pairs and conversational fill words

    oai_token-act-pair · gemini-2.0-flash

    colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ondi
    -0.47
    Schedulers
    -0.47
    ransition
    -0.47
     ID
    -0.46
     tags
    -0.45
    entuk
    -0.45
    xnn
    -0.45
    TabIndex
    -0.45
    ode
    -0.45
     đâu
    -0.45
    POSITIVE LOGITS
    getMenuInflater
    0.57
     becauſe
    0.57
    principalColumn
    0.56
     Theſe
    0.55
    hamshire
    0.54
     Monfieur
    0.52
     AssemblyProduct
    0.52
    RectangleBorder
    0.52
     itſelf
    0.50
     Eſ
    0.49
    Activations Density 0.124%

    No Known Activations