© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13089
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with criminal sentencing and court proceedings

    oai_token-act-pair · gemini-2.0-flash

    sentence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     convicts
    -1.01
     prison
    -0.98
     convict
    -0.94
     Prison
    -0.92
    Prison
    -0.91
     convicted
    -0.89
     prisons
    -0.86
     inmate
    -0.82
    prison
    -0.81
     inmates
    -0.80
    POSITIVE LOGITS
    تقاوى
    0.57
    webElementXpaths
    0.54
    aarrggbb
    0.52
    发表于
    0.51
    saraba
    0.50
    localPosition
    0.49
    masing
    0.49
    ricians
    0.49
    multer
    0.48
    }:${
    0.48
    Activations Density 0.918%

    No Known Activations