© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10282
    Prev
    Next
    INDEX
    Explanations

    legal and bureaucratic language

    oai_token-act-pair · gemini-2.0-flash

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     estekak
    -0.60
    fromnode
    -0.54
    Välislingid
    -0.52
    页面存档备份
    -0.48
    applied
    -0.48
    udian
    -0.48
    nonatomic
    -0.47
    rum
    -0.47
     propOrder
    -0.47
     ligiloj
    -0.46
    POSITIVE LOGITS
     الحره
    0.70
    igslist
    0.53
     مواليد
    0.53
    RenderAtEndOf
    0.51
     يتيمه
    0.49
    Datuak
    0.48
    MLLoader
    0.47
    enderror
    0.45
     ""],
    0.45
    AndEndTag
    0.44
    Activations Density 0.978%

    No Known Activations