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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3205
    Prev
    Next
    INDEX
    Explanations

    Latex code, particularly related to math formulas and underlinings

    oai_token-act-pair · gemini-2.0-flash

    Code formatting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     IndexPath
    -0.47
    ıştı
    -0.45
    νας
    -0.45
     render
    -0.44
    uez
    -0.44
    輌
    -0.43
    ual
    -0.42
    raising
    -0.42
    وط
    -0.42
    ované
    -0.42
    POSITIVE LOGITS
    +#+#
    0.92
     متعلقه
    0.83
    出版年
    0.79
     تضيفلها
    0.74
    lgari
    0.69
    RTEX
    0.66
    addPreferredGap
    0.66
     betweenstory
    0.62
    تفصیلات
    0.60
     Wiktionnaire
    0.60
    Activations Density 0.066%

    No Known Activations