© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2529
    Prev
    Next
    INDEX
    Explanations

    lists of objects, especially when those objects are being used for some action.

    oai_token-act-pair · gemini-2.0-flash

    tangible objects or containers

    np_token-act-pair-logits · gpt-4o-mini

    the article "a"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Audiodateien
    -0.87
    حياتها
    -0.68
     &___
    -0.66
     onCreateView
    -0.63
     intérieure
    -0.62
    Obrázky
    -0.61
    Gambas
    -0.61
     becauſe
    -0.61
    σμο
    -0.61
    stateProvider
    -0.59
    POSITIVE LOGITS
     piece
    0.64
     pile
    0.60
     stack
    0.57
     bag
    0.54
     PIECE
    0.52
     book
    0.50
     bin
    0.50
     bottle
    0.50
     puddle
    0.49
     wad
    0.48
    Activations Density 1.871%

    No Known Activations