© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10869
    Prev
    Next
    INDEX
    Explanations

    mentions of instances or possibilities

    oai_token-act-pair · gemini-2.0-flash

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     fili
    -0.52
     He
    -0.50
    quilla
    -0.48
     works
    -0.47
     so
    -0.47
     he
    -0.47
     worked
    -0.47
    역
    -0.46
     work
    -0.46
    енты
    -0.46
    POSITIVE LOGITS
     BoxDecoration
    0.82
     فريبيس
    0.79
     pouvoit
    0.75
     CURIAM
    0.75
    Datuak
    0.75
     auroit
    0.74
     feroit
    0.73
     Monfieur
    0.73
     prenn
    0.72
     marbre
    0.71
    Activations Density 0.484%

    No Known Activations