© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3452
    Prev
    Next
    INDEX
    Explanations

    legal language related to criminal charges and court proceedings

    oai_token-act-pair · gemini-2.0-flash

    charges

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Datuak
    -0.68
    WireFormatLite
    -0.65
    
    -0.64
     propOrder
    -0.59
    __':
    -0.58
    ΗΣ
    -0.58
     تضيفلها
    -0.57
    ISupport
    -0.57
     licenses
    -0.56
    ργο
    -0.55
    POSITIVE LOGITS
     charge
    0.55
    charge
    0.54
     charges
    0.50
    charges
    0.50
    šné
    0.46
    icolo
    0.45
    chik
    0.43
    ecko
    0.42
    phazard
    0.42
     c
    0.42
    Activations Density 2.526%

    No Known Activations