© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11273
    Prev
    Next
    INDEX
    Explanations

    references containing author initials, journal abbreviations, and numbers

    oai_token-act-pair · gemini-2.0-flash

    climate and geography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     "..\..\..\
    -0.74
    تقاوى
    -0.64
    #+#
    -0.63
     Meksiku
    -0.62
    PreferredItem
    -0.56
    WebElementEntity
    -0.55
    NameInMap
    -0.55
     initComponents
    -0.51
     "..\..\
    -0.49
    ->___
    -0.49
    POSITIVE LOGITS
    Climate
    0.55
     Oceanography
    0.55
     Meteorology
    0.54
     Climatic
    0.54
     CLIMATE
    0.53
    География
    0.52
    Continent
    0.52
     Geology
    0.52
     GEOLOGY
    0.51
     Climate
    0.50
    Activations Density 9.834%

    No Known Activations