© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14737
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" in different contexts, sometimes near celestial or religious terms

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Obtén
    -0.79
     Efq
    -0.70
     initComponents
    -0.65
    ?—
    -0.59
     zoos
    -0.57
     reft
    -0.56
     sceptre
    -0.56
     Dijo
    -0.56
     Pingback
    -0.56
     Protestantism
    -0.55
    POSITIVE LOGITS
    IntoConstraints
    0.59
    RESUMO
    0.53
    OGND
    0.50
    ServletException
    0.47
    forName
    0.47
     garde
    0.47
     متعلقه
    0.47
    GRANTED
    0.46
    IVEREF
    0.46
    ernacle
    0.46
    Activations Density 4.246%

    No Known Activations