© 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. 12074
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas, often containing Greek letters and subscripts

    oai_token-act-pair · gemini-2.0-flash

    Math and code

    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
    ukkah
    -0.51
     world
    -0.51
     int
    -0.50
     insist
    -0.47
     getInt
    -0.46
     Valentín
    -0.46
    brunn
    -0.45
     share
    -0.43
    ianum
    -0.43
    FLICT
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.73
    CppMethod
    0.73
    grà
    0.69
     propOrder
    0.68
    IntoConstraints
    0.65
    oredCriteria
    0.65
    SequentialGroup
    0.64
     pinulongan
    0.63
     Chwiliwch
    0.63
    ValueStyle
    0.62
    Activations Density 2.386%

    No Known Activations