© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5997
    Prev
    Next
    INDEX
    Explanations

    words that are related to schools, and in particular, student life on campus

    oai_token-act-pair · gemini-2.0-flash

    Student/campus related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IntoConstraints
    -0.64
    nitts
    -0.61
    parsedMessage
    -0.60
    出版年
    -0.58
     @"/
    -0.58
     MainAxisSize
    -0.57
    Források
    -0.57
     *__
    -0.56
    ंदीखरीदारी
    -0.55
    $^{\
    -0.54
    POSITIVE LOGITS
     Paglinawan
    0.53
    soort
    0.51
     US
    0.47
    upassen
    0.44
    protoimpl
    0.44
    uvo
    0.44
    teng
    0.43
    ->_
    0.43
    stest
    0.43
     Royal
    0.43
    Activations Density 1.977%

    No Known Activations