© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7761
    Prev
    Next
    INDEX
    Explanations

    technical language used in scientific papers, particularly in physics

    oai_token-act-pair · gemini-2.0-flash

    quantum energy transport

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.13
     dAtA
    -0.62
    NegativeButton
    -0.53
    SharedCtor
    -0.52
     صوتيه
    -0.50
     nahilalakip
    -0.50
     skai
    -0.50
    WriteBarrier
    -0.49
     would
    -0.48
    LookAnd
    -0.46
    POSITIVE LOGITS
    $.
    0.68
    NUMX
    0.67
     مشين
    0.65
    endpush
    0.63
    $$
    0.63
    clearInterval
    0.60
    ESR
    0.60
    BibitemShut
    0.59
    ElementException
    0.58
     Mbps
    0.58
    Activations Density 5.376%

    No Known Activations