© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5972
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to technology, advertisements, trends, and future predictions

    oai_token-act-pair · gemini-2.0-flash

    stickers

    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
    Lähteet
    -0.73
    OGND
    -0.69
     فريبيس
    -0.58
     estekak
    -0.58
     Мексичка
    -0.56
     BnF
    -0.54
    UrlResolution
    -0.54
    TargetException
    -0.54
     resourceCulture
    -0.52
    Sklici
    -0.52
    POSITIVE LOGITS
    มาะ
    0.57
    endiri
    0.55
    imageshack
    0.54
    avantage
    0.52
     Besøkt
    0.51
     betweenstory
    0.49
    RuleContext
    0.48
    bardziej
    0.48
     సౌకర్య
    0.47
     Lainnya
    0.47
    Activations Density 18.678%

    No Known Activations