© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15633
    Prev
    Next
    INDEX
    Explanations

    things related to culture

    oai_token-act-pair · gemini-2.0-flash

    terms related to cultural heritage

    np_token-act-pair-logits · gpt-4o-mini

    cultural

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    adaptiveStyles
    -0.59
     occidentalis
    -0.58
     western
    -0.56
    stateMutability
    -0.53
    ecap
    -0.52
    rät
    -0.48
     Caledonia
    -0.46
     Western
    -0.46
    deinit
    -0.46
    хие
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.61
    inigungs
    0.56
    ineno
    0.54
     <",
    0.52
    Hauptartikel
    0.52
    ArgsConstructor
    0.52
    esModule
    0.50
    tagHelper
    0.50
     ThemeData
    0.49
     intptr
    0.48
    Activations Density 1.057%

    No Known Activations