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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1837
    Prev
    Next
    INDEX
    Explanations

    text referring to computing

    oai_token-act-pair · gemini-2.0-flash

    computer-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Computer
    -2.03
    Computer
    -1.96
     computer
    -1.94
     COMPUTER
    -1.84
    computer
    -1.81
     Computers
    -1.78
    COMPUTER
    -1.73
    Computers
    -1.70
     computers
    -1.69
     Electronic
    -1.59
    POSITIVE LOGITS
    BeginContext
    0.66
    elola
    0.52
    bigsqcup
    0.48
    LookAnd
    0.47
     noqa
    0.47
    stwie
    0.46
    Toole
    0.46
    ][$
    0.46
    RTSC
    0.45
    σιμοποι
    0.45
    Activations Density 4.316%

    No Known Activations