© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11502
    Prev
    Next
    INDEX
    Explanations

    words that end in "ed" or include "th" but are not stop words.

    oai_token-act-pair · gemini-2.0-flash

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    -0.90
     Administrativna
    -0.89
     estekak
    -0.85
     ujednoznacz
    -0.85
    Geplaatst
    -0.80
     kasarigan
    -0.79
     defaultstate
    -0.78
    UnitTesting
    -0.78
    verwijspagina
    -0.77
     intptr
    -0.75
    POSITIVE LOGITS
    bootstrapcdn
    0.47
     foam
    0.45
    נן
    0.43
     fuori
    0.43
     foaming
    0.41
     निर्माण
    0.41
    kreuz
    0.40
     North
    0.40
     promotion
    0.40
     charged
    0.40
    Activations Density 0.883%

    No Known Activations