© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4769
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating people described as targets of negative actions

    oai_token-act-pair · gemini-2.0-flash

    target

    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
    webElementXpaths
    -0.86
    EDEFAULT
    -0.71
     nahilalakip
    -0.63
    RegressionTest
    -0.61
    adpleegd
    -0.59
    migrationBuilder
    -0.59
     ProtoMessage
    -0.59
     oprot
    -0.57
    IUrlHelper
    -0.56
     ModelExpression
    -0.56
    POSITIVE LOGITS
     target
    2.39
     targets
    2.16
    target
    2.11
     Target
    1.95
    Target
    1.94
    TARGET
    1.80
     Targets
    1.77
     TARGET
    1.76
    targets
    1.75
    Targets
    1.62
    Activations Density 1.883%

    No Known Activations