© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14196
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by articles pronouns or numbers

    oai_token-act-pair · gemini-2.0-flash

    numbers and their ordinal forms

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

    in

    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
    oneofs
    -0.79
    ItemBackground
    -0.73
     незавершена
    -0.70
    IntoConstraints
    -0.63
    SequentialGroup
    -0.63
     ISNI
    -0.63
     дописавши
    -0.63
     Wiktionnaire
    -0.63
    hoeddwyd
    -0.63
    RectangleBorder
    -0.62
    POSITIVE LOGITS
     six
    1.18
     two
    1.16
     three
    1.13
     five
    1.07
     four
    1.05
     seven
    0.99
     eight
    0.99
    three
    0.92
     deux
    0.92
    four
    0.88
    Activations Density 1.520%

    No Known Activations