© 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. 11708
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating the passage of time or something that is current in society

    oai_token-act-pair · gemini-2.0-flash

    recently

    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
     until
    -0.72
    Until
    -0.71
     Until
    -0.65
    until
    -0.65
    +#+#
    -0.62
     endblock
    -0.59
     untill
    -0.57
     až
    -0.56
    까지
    -0.56
     jusqu
    -0.55
    POSITIVE LOGITS
     otomatig
    0.68
    ftagPool
    0.66
    mappedBy
    0.63
    forRoot
    0.55
    titleMargin
    0.54
    CppCodeGen
    0.53
    Diweddarwch
    0.52
    wapV
    0.52
    webElementGuid
    0.49
    orthand
    0.49
    Activations Density 33.894%

    No Known Activations