© 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. 8818
    Prev
    Next
    INDEX
    Explanations

    words related to knowledge, awareness, plans, and choices.

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

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

    Questions and uncertainty

    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
    tille
    -0.55
    ÉR
    -0.50
    ori
    -0.47
     gra
    -0.46
    ché
    -0.45
     Gra
    -0.45
    gra
    -0.44
     MUNDO
    -0.44
    tile
    -0.44
     TRABAJO
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.94
    tagHelperRunner
    0.88
    BeginContext
    0.76
    IntoConstraints
    0.75
     hvem
    0.74
    IsContent
    0.73
    SequentialGroup
    0.73
    makeConstraints
    0.71
    LookAnd
    0.70
     XCTest
    0.68
    Activations Density 1.649%

    No Known Activations