© 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. 15661
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that something has existed for a considerable amount of time, often using the word "quite"

    oai_token-act-pair · gemini-2.0-flash

    some

    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
    setVerticalGroup
    -0.60
     numerous
    -0.60
    Numerous
    -0.59
     CURIAM
    -0.59
     Numerous
    -0.57
    큼
    -0.56
     numerosas
    -0.56
    iconque
    -0.55
    ьаж
    -0.54
     continúas
    -0.53
    POSITIVE LOGITS
     some
    1.65
    some
    1.48
    Some
    1.30
     Some
    1.27
     SOME
    1.13
    SOME
    1.11
     sometime
    1.02
     algum
    0.93
     Sometime
    0.88
     algún
    0.82
    Activations Density 3.709%

    No Known Activations