© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4861
    Prev
    Next
    INDEX
    Explanations

    mentions of groups of people, specifically finding adjectives and nouns describing the group

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     démocr
    -0.66
    )}</
    -0.64
    MergeFrom
    -0.63
    CodeAttribute
    -0.61
    endphp
    -0.59
     mascota
    -0.59
    migrationBuilder
    -0.59
    "}>
    -0.57
    IsContent
    -0.56
    StructEnd
    -0.56
    POSITIVE LOGITS
     persons
    0.74
     people
    0.73
     fellows
    0.69
     men
    0.69
     experts
    0.66
     professionals
    0.65
     adults
    0.64
     individuals
    0.64
     fellow
    0.63
     scholars
    0.62
    Activations Density 1.485%

    No Known Activations