© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10212
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to social and political science

    oai_token-act-pair · gemini-2.0-flash

    and/or commas

    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
     disambiguazione
    -0.79
    StoryboardSegue
    -0.74
     utafitiHapana
    -0.72
     Italijanski
    -0.71
    InitVars
    -0.69
     незавершена
    -0.65
    ItemBackground
    -0.63
    WithIOException
    -0.63
    webElementXpaths
    -0.63
     المعيارى
    -0.61
    POSITIVE LOGITS
     MainAxisSize
    0.55
    RectangleBorder
    0.52
    colgroup
    0.49
     Usaha
    0.46
    stylesheet
    0.45
     representative
    0.42
    aps
    0.41
    sibles
    0.40
     Stunde
    0.40
    出会
    0.39
    Activations Density 9.655%

    No Known Activations