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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 919
    Prev
    Next
    INDEX
    Explanations

    words and phrases that often appear in instruction manuals or advertising copy, especially those involving prices and purchases

    oai_token-act-pair · gemini-2.0-flash

    non-English

    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
     ExecuteAsync
    -0.76
    tvguidetime
    -0.69
    =_
    -0.66
     BrowserModule
    -0.64
     ProtoMessage
    -0.64
     &_
    -0.62
    — 
    -0.62
     *_
    -0.62
    };*/
    -0.62
     Himo
    -0.59
    POSITIVE LOGITS
     chré
    0.60
     laikā
    0.60
     démocr
    0.57
     päivä
    0.57
     enfans
    0.57
     pauvres
    0.57
     löyty
    0.57
     humaines
    0.57
     religieuses
    0.57
     espirituales
    0.56
    Activations Density 4.001%

    No Known Activations