© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11912
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to behaviors, often undesirable ones, of people or children

    oai_token-act-pair · gemini-2.0-flash

    behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    findpost
    -0.69
     BoxFit
    -0.57
    ↩
    -0.56
     Vikipedi
    -0.55
    bindValue
    -0.54
    ghu
    -0.54
    mless
    -0.53
    enumi
    -0.53
    piac
    -0.50
    ộn
    -0.49
    POSITIVE LOGITS
    WebVitals
    0.63
     disobedience
    0.55
     delinquency
    0.54
    ceğini
    0.54
     punished
    0.50
    ymal
    0.49
    WithIOException
    0.49
     rebellion
    0.49
     ivelany
    0.48
     étu
    0.47
    Activations Density 1.427%

    No Known Activations