© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14740
    Prev
    Next
    INDEX
    Explanations

    text referencing both newspapers and royalty

    oai_token-act-pair · gemini-2.0-flash

    Royalty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     royal
    -2.36
     Royal
    -2.20
    royal
    -2.14
     ROYAL
    -2.11
    Royal
    -2.09
     King
    -2.08
     king
    -2.06
     KING
    -2.05
     Kings
    -1.99
     queen
    -1.98
    POSITIVE LOGITS
     Spra
    0.47
     Tempe
    0.45
     Gord
    0.42
    WriteTagHelper
    0.42
    ).—
    0.41
     Debre
    0.40
    ducción
    0.40
     Hibernate
    0.39
     ffilmiau
    0.39
    noscript
    0.38
    Activations Density 1.339%

    No Known Activations