© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 88
    Prev
    Next
    INDEX
    Explanations

    numbers

    oai_token-act-pair · gemini-2.0-flash

    single digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ReusableCell
    -0.65
    __(/*!
    -0.63
    AddTagHelper
    -0.63
     CreateTagHelper
    -0.62
    GraphicsUnit
    -0.62
    principalColumn
    -0.60
    tvguidetime
    -0.57
     समीक्षक
    -0.56
     intptr
    -0.56
     otomatig
    -0.55
    POSITIVE LOGITS
    み
    0.51
    とも
    0.44
    pidou
    0.44
    lccn
    0.42
     magnet
    0.41
     Copernicus
    0.41
    spell
    0.41
    例句
    0.40
    Flip
    0.39
    kheim
    0.39
    Activations Density 19.366%

    No Known Activations