© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3103
    Prev
    Next
    INDEX
    Explanations

    text related to books, reading, or education, frequently referencing authors or the current week.

    oai_token-act-pair · gemini-2.0-flash

    Written content

    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
    ValueStyle
    -0.77
     оригіналу
    -0.67
    PerformLayout
    -0.64
    Geplaatst
    -0.63
    PDOException
    -0.61
    prepareStatement
    -0.57
    ::::::::
    -0.56
    rawDesc
    -0.56
     Савезне
    -0.56
    +#+#
    -0.54
    POSITIVE LOGITS
     chapter
    0.55
     article
    0.52
     app
    0.50
     Chapter
    0.47
    曖昧さ回避
    0.47
     artigo
    0.46
    InfoWindow
    0.46
    reportWebVitals
    0.44
     applet
    0.44
     divertente
    0.44
    Activations Density 4.421%

    No Known Activations