© 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. 4050
    Prev
    Next
    INDEX
    Explanations

    mentions of investigations, accusations, and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    incidents/crises

    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
    UserScript
    -0.81
    -------------</
    -0.65
    ništvo
    -0.61
    \{\\
    -0.58
    oredCriteria
    -0.54
     ddelweddau
    -0.53
     <<<<<<<<<<<<<<
    -0.52
     osserva
    -0.50
     déclar
    -0.50
     Says
    -0.50
    POSITIVE LOGITS
     stirred
    0.57
     تانيه
    0.56
     rocked
    0.56
    Demografie
    0.55
     thrust
    0.55
     sent
    0.53
     roused
    0.52
     provoked
    0.52
    ensement
    0.50
    simplex
    0.50
    Activations Density 1.490%

    No Known Activations