© 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. 1709
    Prev
    Next
    INDEX
    Explanations

    words related to protection from harmful environmental factors or dangers, and words related to head coverings for sports.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    adaptiveStyles
    -0.52
    Външни
    -0.51
    giarism
    -0.49
     Familienname
    -0.47
    셜
    -0.47
    nių
    -0.46
     JpaRepository
    -0.46
     råd
    -0.45
     PackageManager
    -0.45
     wavelet
    -0.44
    POSITIVE LOGITS
     keep
    1.64
     kept
    1.59
    keep
    1.54
     keeping
    1.54
     Keep
    1.52
    Keep
    1.47
     keeps
    1.45
     KEEP
    1.42
    KEEP
    1.41
    kept
    1.41
    Activations Density 3.095%

    No Known Activations