© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13781
    Prev
    Next
    INDEX
    Explanations

    words heavily related to the game of golf.

    oai_token-act-pair · gemini-2.0-flash

    golf

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     culoare
    -0.59
     inoxidable
    -0.58
    CloseOperation
    -0.58
     كومونز
    -0.57
     externi
    -0.57
     yetu
    -0.57
     kyse
    -0.56
     pouvoit
    -0.55
     chi̍t
    -0.54
     florales
    -0.54
    POSITIVE LOGITS
     CreateTagHelper
    0.60
    tish
    0.55
    keyColumn
    0.51
    ftest
    0.51
    命
    0.51
     Fire
    0.50
    gouv
    0.49
    سطس
    0.49
    WithIOException
    0.49
    Sti
    0.48
    Activations Density 1.013%

    No Known Activations