© 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. 9484
    Prev
    Next
    INDEX
    Explanations

    words and phrases from scientific or engineering publications that include numbers, measurements, or quantitative analysis.

    oai_token-act-pair · gemini-2.0-flash

    technical passages

    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
     للاسماء
    -0.69
     صوتيه
    -0.63
    Autoritní
    -0.63
    اقرأ
    -0.59
     resourceCulture
    -0.56
     برانيه
    -0.56
    +#+#
    -0.54
    verwijspagina
    -0.54
     incomplète
    -0.52
    TagMode
    -0.52
    POSITIVE LOGITS
    ({})
    0.57
    =()
    0.57
    (_,
    0.55
    (()
    0.54
    ved
    0.54
     [],
    0.53
    +:+
    0.53
    ilen
    0.53
    zonych
    0.51
    apeno
    0.51
    Activations Density 46.341%

    No Known Activations