© 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. 10155
    Prev
    Next
    INDEX
    Explanations

    words related to membership in a group

    oai_token-act-pair · gemini-2.0-flash

    Categories of people

    np_max-act · gemini-2.0-flash

    groups of people

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     skiers
    -1.60
     hikers
    -1.58
     golfers
    -1.57
     vegans
    -1.52
     anglers
    -1.45
     atheists
    -1.44
     commuters
    -1.42
     feminists
    -1.41
     gamers
    -1.41
     rappers
    -1.40
    POSITIVE LOGITS
     personal
    0.71
    hips
    0.69
     who
    0.66
     responsible
    0.65
     professional
    0.62
     member
    0.58
     recent
    0.57
     general
    0.55
    NewUrlParser
    0.54
     and
    0.53
    Activations Density 4.598%

    No Known Activations