© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11017
    Prev
    Next
    INDEX
    Explanations

    parts of a document that contain URLs/links to documentation or tutorials

    oai_token-act-pair · gemini-2.0-flash

    links or references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ツ
    -0.47
     laikā
    -0.47
    rog
    -0.46
    UnitTesting
    -0.46
    gtest
    -0.43
    %)$
    -0.40
     reager
    -0.38
    imp
    -0.38
    alan
    -0.37
    gest
    -0.37
    POSITIVE LOGITS
    EndGlobalSection
    0.82
     насељу
    0.77
    __(/*!
    0.75
    BeginContext
    0.71
    onViewCreated
    0.68
    omeness
    0.68
    -------------</
    0.67
    wpi
    0.67
    DoubleQuotes
    0.66
    TagMode
    0.65
    Activations Density 2.299%

    No Known Activations