© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2110
    Prev
    Next
    INDEX
    Explanations

    words and phrases common in legal documents, especially court opinions.

    oai_token-act-pair · gemini-2.0-flash

    "set"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     препратки
    -0.68
     NSCoder
    -0.66
     CreateTagHelper
    -0.54
    RenderAtEndOf
    -0.52
    +#+#
    -0.48
    IGraphics
    -0.46
     lenker
    -0.44
    EndTag
    -0.44
    lapia
    -0.44
    giarism
    -0.43
    POSITIVE LOGITS
     set
    3.02
     Set
    2.81
    set
    2.61
    Set
    2.58
     sets
    2.50
     SET
    2.48
     Sets
    2.36
    SET
    2.27
    sets
    2.19
    Sets
    2.11
    Activations Density 6.984%

    No Known Activations