© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11629
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially people's names, and political terms

    oai_token-act-pair · gemini-2.0-flash

    Historical/political events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    UnsafeEnabled
    -0.78
     tantum
    -0.51
    IsContent
    -0.51
    <bos>
    -0.51
     Matta
    -0.48
     Tại
    -0.47
    NamedQuery
    -0.47
    enaus
    -0.46
     Constantinople
    -0.46
     automatique
    -0.45
    POSITIVE LOGITS
    Personensuche
    0.91
     متعلقه
    0.84
    Tembelea
    0.79
    +#+#
    0.65
    rungsseite
    0.63
    сылкі
    0.60
     חיצוניים
    0.59
    Jegyzetek
    0.59
    Билгалдахарш
    0.59
     تانيه
    0.59
    Activations Density 0.693%

    No Known Activations