© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14663
    Prev
    Next
    INDEX
    Explanations

    words related to current events and entities

    oai_token-act-pair · gemini-2.0-flash

    formal communication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     disambiguazione
    -0.66
     CURIAM
    -0.63
     كومونز
    -0.61
    "){
    -0.61
    elesai
    -0.60
     Theſe
    -0.60
     esternos
    -0.60
    |}{$
    -0.59
    Filmographie
    -0.59
     ngan
    -0.59
    POSITIVE LOGITS
     called
    0.61
     jakim
    0.52
     (
    0.47
     namely
    0.47
    XmlType
    0.47
    called
    0.47
     olan
    0.44
    GetAxis
    0.44
     named
    0.44
    AutoScale
    0.44
    Activations Density 1.140%

    No Known Activations