© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1808
    Prev
    Next
    INDEX
    Explanations

    a story, as well as words related to plots and characters

    oai_token-act-pair · gemini-2.0-flash

    book excerpts

    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
     UIT
    -0.60
    WriteLiteral
    -0.57
     Carry
    -0.56
     initComponents
    -0.55
    raise
    -0.54
    complete
    -0.53
    saraba
    -0.52
     приве
    -0.52
    Carry
    -0.52
     XCTest
    -0.51
    POSITIVE LOGITS
    Personendaten
    0.59
     يتيمه
    0.57
    OGND
    0.55
    वरण
    0.51
     himo
    0.50
    makeatletter
    0.49
     Audiodateien
    0.48
    Numerology
    0.47
    ğan
    0.46
    archiviato
    0.44
    Activations Density 6.985%

    No Known Activations