© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10491
    Prev
    Next
    INDEX
    Explanations

    legal and criminal terms, especially related to the criminal justice system

    oai_token-act-pair · gemini-2.0-flash

    criminal

    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
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.65
     autorytatywna
    -0.62
    ngdoc
    -0.55
    PreferredItem
    -0.54
    PasswordEncoder
    -0.52
    wanda
    -0.51
     NSObject
    -0.50
    QtGui
    -0.50
    PERTIES
    -0.49
    haustible
    -0.49
    POSITIVE LOGITS
    
    0.61
    Portály
    0.53
    立た
    0.48
     Krzyż
    0.47
     columnIndex
    0.47
     darah
    0.46
    MENAFN
    0.46
    InSection
    0.46
    Mines
    0.44
    κτη
    0.44
    Activations Density 1.989%

    No Known Activations