© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11576
    Prev
    Next
    INDEX
    Explanations

    function words and verbs that form the structure of an argument or extended idea.

    oai_token-act-pair · gemini-2.0-flash

    work

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    parsedMessage
    -0.71
    Tikang
    -0.71
    webElementXpaths
    -0.68
     GenerationType
    -0.66
    Hozzáférés
    -0.65
    RenderAtEndOf
    -0.64
    sidemargin
    -0.63
    Datuak
    -0.63
    providedIn
    -0.61
    Personendaten
    -0.60
    POSITIVE LOGITS
     work
    3.03
    work
    2.61
    Work
    2.44
     Work
    2.38
     WORK
    2.19
    WORK
    2.03
     trabajo
    1.82
     trabalho
    1.72
     Arbeit
    1.70
     lavoro
    1.66
    Activations Density 2.243%

    No Known Activations