© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15914
    Prev
    Next
    INDEX
    Explanations

    words related to hydrology, rainfall, and water flow

    oai_token-act-pair · gemini-2.0-flash

    Forests and water flow

    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
     AssemblyCompany
    -0.84
    Geplaatst
    -0.74
    Jereo
    -0.65
     Мексичка
    -0.65
    TagMode
    -0.65
     AssemblyCulture
    -0.63
    AsUp
    -0.63
    DockStyle
    -0.62
    Sucesor
    -0.61
    kloped
    -0.58
    POSITIVE LOGITS
    inci
    0.50
     låg
    0.49
     sää
    0.49
     paik
    0.47
     Landschaft
    0.46
     meille
    0.45
     отделение
    0.44
     ajan
    0.43
     hindurch
    0.43
     šk
    0.43
    Activations Density 6.182%

    No Known Activations