© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10879
    Prev
    Next
    INDEX
    Explanations

    words related to physical locations, facilities, and property

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "with"

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

    Places or areas

    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
    featureID
    -0.94
    abestanden
    -0.94
    RegistryLite
    -0.93
    DeleteBehavior
    -0.77
    WebMethod
    -0.77
     kaynağından
    -0.76
    AccessorTable
    -0.76
     tartalomajánló
    -0.71
    MessageTagHelper
    -0.69
     ModelExpression
    -0.69
    POSITIVE LOGITS
     with
    0.95
     avec
    0.68
     WITH
    0.59
     với
    0.56
     dengan
    0.53
    with
    0.52
     With
    0.50
    run
    0.50
    With
    0.50
     עם
    0.48
    Activations Density 1.758%

    No Known Activations