© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9064
    Prev
    Next
    INDEX
    Explanations

    the word "act" or "acting," sometimes in the context of behaviors, articles, and actions

    oai_token-act-pair · gemini-2.0-flash

    act

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     الحره
    -1.16
     Signalez
    -0.80
    WebElementEntity
    -0.79
     doubtnut
    -0.77
    ViewFeatures
    -0.76
     geox
    -0.75
    DataAnnotations
    -0.75
     FishBase
    -0.75
     Савезне
    -0.75
    =$?
    -0.74
    POSITIVE LOGITS
     B
    0.47
     He
    0.43
     F
    0.40
    oulos
    0.40
     i
    0.40
     
    0.40
    udra
    0.40
     the
    0.39
     or
    0.39
    ландия
    0.39
    Activations Density 3.947%

    No Known Activations