© 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. 15785
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to violence, crime, and capture

    oai_token-act-pair · gemini-2.0-flash

    violence, crime

    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
     كومونز
    -0.51
    ViewImports
    -0.50
     Hach
    -0.47
     prey
    -0.46
    trop
    -0.44
    FormTagHelper
    -0.44
     Kuns
    -0.44
     pinulongan
    -0.42
     victim
    -0.42
    da
    -0.42
    POSITIVE LOGITS
    发表于
    0.72
    yorsunuz
    0.66
     capuche
    0.59
    CUSSION
    0.57
     resourceCulture
    0.56
    sendRedirect
    0.54
    правка
    0.54
    ))[
    0.54
     eléctricos
    0.53
    ();?>
    0.52
    Activations Density 7.257%

    No Known Activations