© 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. 6649
    Prev
    Next
    INDEX
    Explanations

    numerical digits and legal jargon

    oai_token-act-pair · gemini-2.0-flash

    Legal case documents

    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
    Geplaatst
    -0.94
    TagMode
    -0.89
     مشين
    -0.84
    oneofs
    -0.74
    BeginContext
    -0.69
     lenker
    -0.68
    rawDesc
    -0.66
    出版年
    -0.65
    IsContent
    -0.65
    tagext
    -0.64
    POSITIVE LOGITS
    ಿದೆ
    0.50
    JRadioButton
    0.49
     Tro
    0.49
     beina
    0.48
     geïsole
    0.48
     T
    0.47
     தெ
    0.45
     afges
    0.45
     szko
    0.45
     omge
    0.45
    Activations Density 6.514%

    No Known Activations