© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11617
    Prev
    Next
    INDEX
    Explanations

    the word "equivalent" along with words used in technical writing and specialized fields such as medicine, computer science, and military applications.

    oai_token-act-pair · gemini-2.0-flash

    equivalent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    BeginContext
    -1.13
    MLLoader
    -1.11
    InjectAttribute
    -1.11
     متعلقه
    -1.09
    rungsseite
    -1.05
    RectangleBorder
    -1.02
    RenderAtEndOf
    -1.00
     snippetHide
    -0.97
     للمعارف
    -0.96
    ✨:
    -0.95
    POSITIVE LOGITS
     the
    0.78
     and
    0.72
     her
    0.67
     in
    0.67
    ,
    0.63
     A
    0.62
    /
    0.61
    -
    0.61
     a
    0.57
    ing
    0.56
    Activations Density 1.799%

    No Known Activations