© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5328
    Prev
    Next
    INDEX
    Explanations

    the word "as" in a variety of contexts.

    oai_token-act-pair · gemini-2.0-flash

    how something is represented

    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
    Geplaatst
    -0.57
    Gambas
    -0.53
     ComVisible
    -0.53
     perch
    -0.47
    Сюжет
    -0.46
    bangan
    -0.46
    WebElementEntity
    -0.46
     出版
    -0.45
    measuring
    -0.44
    prüche
    -0.43
    POSITIVE LOGITS
     reflected
    1.42
     represented
    1.30
     indicated
    1.28
     embodied
    1.16
     contained
    1.13
     hinted
    1.12
     demonstrated
    1.11
    indicated
    1.11
     exemplified
    1.09
     symbolized
    1.09
    Activations Density 8.334%

    No Known Activations