© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14250
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to legal proceedings and negative outcomes within them.

    oai_token-act-pair · gemini-2.0-flash

    rise

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    RenderAtEndOf
    -0.85
    IBOutlet
    -0.68
     AttributeSet
    -0.63
    jspx
    -0.56
    TagHelpers
    -0.54
     Das
    -0.53
    amerikanischer
    -0.53
    (!__
    -0.52
     QName
    -0.52
     Hame
    -0.51
    POSITIVE LOGITS
     rises
    0.73
     rise
    0.72
    Rise
    0.62
     Rise
    0.61
    rises
    0.61
     RISE
    0.60
     amounts
    0.54
    RISE
    0.53
    rise
    0.52
    المراجع
    0.52
    Activations Density 5.235%

    No Known Activations