© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7964
    Prev
    Next
    INDEX
    Explanations

    language related to law enforcement and crime

    oai_token-act-pair · gemini-2.0-flash

    terms related to theft and crime prevention

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

    authority figures

    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
    FormTagHelper
    -0.69
    
    -0.57
     digitais
    -0.55
    inSlope
    -0.51
    PMailer
    -0.50
    ⓘ
    -0.48
    unknownFields
    -0.47
     BorderSide
    -0.47
     arkite
    -0.46
     Guill
    -0.46
    POSITIVE LOGITS
     AssemblyTitle
    0.57
    äum
    0.55
     recovered
    0.53
    carts
    0.51
    ustimmung
    0.50
    tic
    0.48
     köz
    0.47
     lan
    0.47
    pur
    0.47
    ")))
    0.47
    Activations Density 3.690%

    No Known Activations