© 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. 4818
    Prev
    Next
    INDEX
    Explanations

    XML tags, especially those related to including headers/footers, as well as Chinese language related to sending content

    oai_token-act-pair · 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
     photolibrary
    -0.63
    NUMX
    -0.57
    octanol
    -0.54
     XNUMX
    -0.52
    MENAFN
    -0.52
     filt
    -0.52
    iconque
    -0.52
     Hopf
    -0.52
    __":
    -0.52
     Audiodateien
    -0.51
    POSITIVE LOGITS
     administrativos
    0.42
     Всё
    0.40
     тё
    0.40
     pelbagai
    0.39
     sanitarios
    0.39
     лёг
    0.37
     estatales
    0.37
     líqu
    0.36
     bahagian
    0.36
     üzere
    0.36
    Activations Density 0.143%

    No Known Activations