© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10874
    Prev
    Next
    INDEX
    Explanations

    words that are part of mathematical formulas, statistical analysis, or legal jargon

    oai_token-act-pair · gemini-2.0-flash

    mathematical/statistical functions and theories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.64
    PositiveButton
    -0.62
    NegativeButton
    -0.58
     désolés
    -0.56
    pagesize
    -0.56
    antity
    -0.56
     ब्रेकडाउन
    -0.52
    pecially
    -0.52
    optString
    -0.51
    olves
    -0.51
    POSITIVE LOGITS
    ponses
    0.64
    rungsseite
    0.62
    balleur
    0.56
    luß
    0.55
    limus
    0.54
    갖
    0.53
    esgue
    0.53
    ToAction
    0.52
     Picchu
    0.51
    Према
    0.50
    Activations Density 2.171%

    No Known Activations