© 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. 11893
    Prev
    Next
    INDEX
    Explanations

    proper nouns that are names of cities, towns, states and schools

    oai_token-act-pair · gemini-2.0-flash

    proper nouns and location names

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

    places and organizations

    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
     town
    -0.99
    bootstrapcdn
    -0.91
    tagHelperRunner
    -0.75
     itſelf
    -0.75
     Normdatei
    -0.73
    SpringBootTest
    -0.71
     TOWN
    -0.71
     myſelf
    -0.69
    fillType
    -0.69
     auffi
    -0.68
    POSITIVE LOGITS
    Pages
    0.49
    rox
    0.46
    PendingIntent
    0.44
    mitives
    0.43
    mite
    0.43
    ಂಡ
    0.43
     fire
    0.43
    Moc
    0.42
    tre
    0.41
    aks
    0.41
    Activations Density 0.551%

    No Known Activations