© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1340
    Prev
    Next
    INDEX
    Explanations

    mentions of social gatherings, events, or stories.

    oai_token-act-pair · gemini-2.0-flash

    conjunctions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     surla
    -0.59
     There
    -0.55
     there
    -0.55
     ujednoznacz
    -0.52
    awtextra
    -0.50
    BeginContext
    -0.48
    aarrggbb
    -0.48
     متعلقه
    -0.47
    There
    -0.45
     THERE
    -0.42
    POSITIVE LOGITS
    %")
    0.72
     most
    0.67
     getAge
    0.67
     chi̍t
    0.62
    %");
    0.60
     newItem
    0.59
     torrents
    0.59
     prieten
    0.59
    vrouw
    0.59
    hoedd
    0.59
    Activations Density 6.823%

    No Known Activations