© 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. 10116
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions describing cycles or sequences

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     المق
    -0.45
    ioca
    -0.43
    Press
    -0.42
    TypedDataSet
    -0.40
     تاب
    -0.37
    ////////////////
    -0.36
     observ
    -0.36
     signals
    -0.35
     pressures
    -0.35
    UCE
    -0.35
    POSITIVE LOGITS
    AddTagHelper
    0.89
    AsUp
    0.87
    featureID
    0.83
    \{\\
    0.83
     OFDb
    0.80
    Демографія
    0.79
    +#+#
    0.79
     surla
    0.77
    Personensuche
    0.73
    aarrggbb
    0.73
    Activations Density 1.223%

    No Known Activations