© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13285
    Prev
    Next
    INDEX
    Explanations

    words associated with towns, especially town names and civic buildings

    oai_token-act-pair · gemini-2.0-flash

    references to towns and buildings

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

    town

    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
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.65
     propOrder
    -0.62
    єра
    -0.46
    TokenNameLBRACE
    -0.43
    thered
    -0.42
    orphism
    -0.42
    ynomial
    -0.42
    orska
    -0.41
    etch
    -0.41
    Packaged
    -0.41
    POSITIVE LOGITS
     indisponible
    0.77
    rungsseite
    0.66
     contextLoads
    0.63
     Zentrum
    0.60
     centri
    0.59
     whence
    0.58
    Cen
    0.56
     surla
    0.56
    })));
    0.56
    MigrationBuilder
    0.56
    Activations Density 1.773%

    No Known Activations