© 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. 3353
    Prev
    Next
    INDEX
    Explanations

    times in the 1:00 to 11:59 range

    oai_token-act-pair · gemini-2.0-flash

    words related to specific structured formats or technical terms

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

    1

    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
    ⓘ
    -0.64
     instants
    -0.56
    ViewFeatures
    -0.56
    ύτε
    -0.53
    useState
    -0.52
    lwjgl
    -0.49
     ansi
    -0.48
     vuitton
    -0.48
    NameInMap
    -0.47
     Batter
    -0.47
    POSITIVE LOGITS
     Walkover
    0.63
    tagext
    0.62
    Enllaces
    0.61
    bewerken
    0.61
     Infórmanos
    0.60
    setViewportView
    0.56
     Scott
    0.53
    webElementXpaths
    0.52
    queryInterface
    0.52
    TableModel
    0.49
    Activations Density 0.542%

    No Known Activations