© 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. 7078
    Prev
    Next
    INDEX
    Explanations

    words related to legal documents, potentially in the context of a car or boat, like searching and warrants

    oai_token-act-pair · gemini-2.0-flash

    contents

    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
    vedev
    -0.58
    findpost
    -0.56
    ficulty
    -0.56
    antonio
    -0.52
    uroy
    -0.51
    glEnd
    -0.51
    SPATH
    -0.50
    qrstuvwxyz
    -0.50
     lượt
    -0.50
     ब्रेकडाउन
    -0.49
    POSITIVE LOGITS
     contents
    1.27
     items
    1.07
     content
    0.97
     Items
    0.96
    contents
    0.93
    Contents
    0.93
     Contents
    0.92
     goods
    0.88
     CONTENTS
    0.87
     ITEMS
    0.84
    Activations Density 2.283%

    No Known Activations