© 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. 6739
    Prev
    Next
    INDEX
    Explanations

    content warnings

    oai_token-act-pair · gemini-2.0-flash

    text-based media

    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
    تقاوى
    -0.77
    protoimpl
    -0.70
    aarrggbb
    -0.61
    ்த்த
    -0.54
     EconPapers
    -0.51
     winkel
    -0.50
    cipar
    -0.49
    帖最后由
    -0.49
     Turki
    -0.48
     CanadaChoose
    -0.48
    POSITIVE LOGITS
    ponses
    0.58
    odles
    0.56
     مواليد
    0.52
     BoxDecoration
    0.52
    csolódó
    0.50
    ORAGE
    0.49
    ItemBackground
    0.48
    слова
    0.48
    Дереккөздер
    0.47
    EDEFAULT
    0.47
    Activations Density 10.386%

    No Known Activations