© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4203
    Prev
    Next
    INDEX
    Explanations

    the word "get" and other words that can accompany get

    oai_token-act-pair · gemini-2.0-flash

    URLs and file references

    np_token-act-pair-logits · gpt-4o-mini

    get

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     dão
    -0.53
    contentLoaded
    -0.53
     eikä
    -0.53
     épaules
    -0.53
     encontraban
    -0.52
    CONSIN
    -0.51
     produisent
    -0.48
    astă
    -0.47
    ScopeManager
    -0.47
    собенности
    -0.47
    POSITIVE LOGITS
    IUrlHelper
    0.64
    uanto
    0.64
     an
    0.59
     the
    0.59
     a
    0.58
    Rüyada
    0.56
     fed
    0.56
    
    0.56
    jgl
    0.56
    served
    0.54
    Activations Density 3.984%

    No Known Activations