© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14007
    Prev
    Next
    INDEX
    Explanations

    the prefix "meta-" in medical or scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    meta

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     transfieras
    -0.71
    enumi
    -0.71
    ValueStyle
    -0.65
    usiai
    -0.60
     disponibilités
    -0.59
     صوتيه
    -0.55
    DeleteBehavior
    -0.55
     insuffisamment
    -0.55
    enumii
    -0.54
    ंदीखरीदारी
    -0.54
    POSITIVE LOGITS
     POM
    0.55
     АН
    0.50
    HasIndex
    0.46
    Personendaten
    0.45
    pom
    0.45
    олові
    0.44
    physical
    0.43
     HAP
    0.43
    VersionUID
    0.42
     physical
    0.41
    Activations Density 0.700%

    No Known Activations