© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5642
    Prev
    Next
    INDEX
    Explanations

    scientific writing with references, mathematical symbols, scaling and discussions of coefficients.

    oai_token-act-pair · gemini-2.0-flash

    programming and technical terms

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

    scientific writing

    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
    новниш
    -0.47
     Stoll
    -0.47
    vgili
    -0.47
    niques
    -0.46
    memberId
    -0.45
    ódź
    -0.45
    cektir
    -0.44
    нений
    -0.44
    miers
    -0.43
     fringe
    -0.43
    POSITIVE LOGITS
     ujednoznacz
    0.73
    protoimpl
    0.69
     فريبيس
    0.63
    ItemBackground
    0.63
     disambiguazione
    0.58
    __':
    0.58
    UnusedPrivate
    0.57
    ValueStyle
    0.55
    awaiter
    0.54
     spagno
    0.53
    Activations Density 4.904%

    No Known Activations