© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7384
    Prev
    Next
    INDEX
    Explanations

    strings of text surrounded by curly brackets with "mathrm"

    oai_token-act-pair · gemini-2.0-flash

    mathrm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    DataPropertyName
    -0.56
     or
    -0.50
    chartInstance
    -0.47
    ípios
    -0.46
    нень
    -0.45
     lead
    -0.43
    ôme
    -0.43
     Lead
    -0.42
    никам
    -0.42
    ilies
    -0.42
    POSITIVE LOGITS
    RectangleBorder
    0.67
    ."));
    0.67
    出版年
    0.66
    GEBURTSDATUM
    0.59
     itſelf
    0.58
    NUMX
    0.58
    ثيق
    0.57
     myſelf
    0.57
     varargin
    0.57
    adaptiveStyles
    0.57
    Activations Density 0.138%

    No Known Activations