© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14002
    Prev
    Next
    INDEX
    Explanations

    mentions of populations of people

    oai_token-act-pair · gemini-2.0-flash

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ashes
    -0.47
    fone
    -0.45
    POC
    -0.43
    umptive
    -0.43
     Meny
    -0.43
    nologies
    -0.41
    IRIS
    -0.41
     Ils
    -0.41
     general
    -0.40
     Amal
    -0.40
    POSITIVE LOGITS
     resourceCulture
    0.85
     ProtoMessage
    0.71
    évaluateur
    0.69
     noDo
    0.66
    sizeCache
    0.65
    TagHelper
    0.57
    InitVars
    0.57
    ThemeOverlay
    0.57
    abestanden
    0.56
    TagMode
    0.56
    Activations Density 0.412%

    No Known Activations