© 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. 6477
    Prev
    Next
    INDEX
    Explanations

    the word "around" and words having a meaning related to trajectory with possible inclusion of words, like "the" that are near "around"

    oai_token-act-pair · gemini-2.0-flash

    around

    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
     around
    -1.55
    Around
    -1.44
     Around
    -1.43
    around
    -1.34
     AROUND
    -1.27
     autour
    -1.24
     alrededor
    -1.24
     torno
    -1.15
    AROUND
    -1.12
     вокруг
    -1.04
    POSITIVE LOGITS
     Paglinawan
    0.62
     the
    0.58
     Signalez
    0.57
    skosten
    0.57
    ADELPHIA
    0.57
    Архівовано
    0.55
    AccessorTable
    0.54
    leyin
    0.54
    FormTagHelper
    0.54
    igor
    0.54
    Activations Density 1.551%

    No Known Activations