© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5542
    Prev
    Next
    INDEX
    Explanations

    descriptions of automotive technical issues and repairs.

    oai_token-act-pair · gemini-2.0-flash

    specific technical terms or jargon

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

    vehicle faults and repairs

    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
    SharedCtor
    -0.64
    DockStyle
    -0.64
    awaiter
    -0.59
    mergeFrom
    -0.56
    Бахар
    -0.56
    Autoritní
    -0.55
    Diweddarwch
    -0.52
    бования
    -0.50
    webElementXpaths
    -0.50
    ABAJO
    -0.50
    POSITIVE LOGITS
     فريبيس
    0.65
     ?>>
    0.53
    erenc
    0.53
    PreAuthorize
    0.48
    itemBuilder
    0.48
    ciaż
    0.46
    ="?
    0.46
     cycl
    0.46
    LICENSE
    0.45
     dips
    0.45
    Activations Density 1.634%

    No Known Activations