© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5163
    Prev
    Next
    INDEX
    Explanations

    sentences about books or studies that include words like "appendices", "chapter", "book", "the", "a" and conjunctions, possibly about activities.

    oai_token-act-pair · gemini-2.0-flash

    book contents

    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
    †
    -0.44
    rng
    -0.40
    yang
    -0.39
     fer
    -0.39
    ミア
    -0.38
    ofman
    -0.38
     Se
    -0.36
     leggen
    -0.35
    Edit
    -0.35
    ńczy
    -0.35
    POSITIVE LOGITS
    orsese
    0.79
    AndEndTag
    0.77
    脚注の使い方
    0.76
    complexType
    0.76
    WebVitals
    0.75
     ModelExpression
    0.74
     contextLoads
    0.70
     culturelles
    0.70
     Chwiliwch
    0.69
     gddr
    0.68
    Activations Density 7.820%

    No Known Activations