© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5302
    Prev
    Next
    INDEX
    Explanations

    words related to violent protest.

    oai_token-act-pair · gemini-2.0-flash

    destruction

    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
    Soorten
    -0.69
    abestanden
    -0.66
    SPJ
    -0.65
    PerformLayout
    -0.65
    POSURE
    -0.64
     Walkover
    -0.63
    RegressionTest
    -0.60
    Geplaatst
    -0.56
     dignité
    -0.56
    حياته
    -0.56
    POSITIVE LOGITS
    μβρίου
    0.46
     tornadoes
    0.46
    JspWriter
    0.45
     Amu
    0.45
    Rhône
    0.44
     panty
    0.44
     handker
    0.44
     Bajo
    0.43
     Habana
    0.43
     Frog
    0.43
    Activations Density 7.475%

    No Known Activations