© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10743
    Prev
    Next
    INDEX
    Explanations

    sentences that contain the word "crime" or discuss racial issues

    oai_token-act-pair · gemini-2.0-flash

    terms related to crime and drugs

    np_token-act-pair-logits · gpt-4o-mini

    crimes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    setContentView
    -0.61
    Eze
    -0.53
     AppModule
    -0.47
     Eze
    -0.45
    vaadin
    -0.45
    րջ
    -0.45
    ätie
    -0.44
    ècie
    -0.44
    Посилання
    -0.44
     Audiodateien
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    0.66
     صوتيه
    0.60
    ună
    0.58
    verwijspagina
    0.57
    MessageTagHelper
    0.57
     narcotics
    0.56
     crimes
    0.56
     drug
    0.55
     homic
    0.55
     narcotic
    0.54
    Activations Density 7.926%

    No Known Activations