© 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. 2340
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to government, accountability, politics or energy issues

    oai_token-act-pair · gemini-2.0-flash

    complaints

    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
     GetEnumerator
    -0.60
    createCanvas
    -0.59
     autorytatywna
    -0.58
    WithIOException
    -0.58
     lenker
    -0.58
    titleMargin
    -0.52
    UnusedPrivate
    -0.50
    saraba
    -0.47
     linkovi
    -0.46
     mã
    -0.45
    POSITIVE LOGITS
    __(/*!
    0.57
     surla
    0.54
     newOwner
    0.53
    itename
    0.50
    一时间
    0.50
    complexContent
    0.49
    hahn
    0.49
    ChildScrollView
    0.49
    ्यालय
    0.48
    Pfalz
    0.48
    Activations Density 6.387%

    No Known Activations