© 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. 4079
    Prev
    Next
    INDEX
    Explanations

    the words "exposure," "tower" and words related to legal trials

    oai_token-act-pair · gemini-2.0-flash

    towers and radiation

    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
     ejus
    -0.71
     ſche
    -0.67
     espagne
    -0.65
     argint
    -0.65
     CHAPITRE
    -0.64
     dezelve
    -0.63
     Jefus
    -0.60
     ainfi
    -0.60
     gjennom
    -0.59
     Bucure
    -0.59
    POSITIVE LOGITS
    antd
    0.77
     فريبيس
    0.76
     Audiodateien
    0.72
    apunov
    0.72
    makeConstraints
    0.71
    HttpFoundation
    0.70
     onCreateView
    0.69
    hematical
    0.69
    %;">
    0.68
    Erreferentziak
    0.66
    Activations Density 3.409%

    No Known Activations