© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8693
    Prev
    Next
    INDEX
    Explanations

    text about replacing brake pads on a vehicle

    oai_token-act-pair · gemini-2.0-flash

    terms related to brake pads

    np_token-act-pair-logits · gpt-4o-mini

    Brakes and clutches

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    MemoryWarning
    -0.90
    +:+
    -0.63
    CppMethod
    -0.60
    PropertyChanging
    -0.59
     resourceCulture
    -0.58
    principalColumn
    -0.57
     NSCoder
    -0.56
     EconPapers
    -0.56
    tvguidetime
    -0.56
     JScrollPane
    -0.55
    POSITIVE LOGITS
     dot
    0.52
    cline
    0.49
    multirow
    0.49
     service
    0.48
    orianCalendar
    0.48
    ПК
    0.47
     legyen
    0.47
    Czytaj
    0.46
    κίνη
    0.46
     ivelany
    0.46
    Activations Density 0.660%

    No Known Activations