© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13577
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal and medical processes, considerations, and factors in decision-making or analysis.

    oai_token-act-pair · gemini-2.0-flash

    "in" in different languages

    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
    SharedCtor
    -0.81
    expandindo
    -0.79
    :✨
    -0.75
     mergeFrom
    -0.68
     lenker
    -0.67
    شهاد
    -0.67
    CPtr
    -0.66
     resourceCulture
    -0.65
     صوتيه
    -0.64
     كومونز
    -0.64
    POSITIVE LOGITS
     in
    1.50
    in
    0.78
     в
    0.74
     In
    0.70
     في
    0.65
     în
    0.65
    In
    0.63
    ใน
    0.63
     در
    0.63
    在
    0.62
    Activations Density 4.227%

    No Known Activations