© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12416
    Prev
    Next
    INDEX
    Explanations

    words and phrases that say something existed in one state but is subsequently changed to another state

    oai_token-act-pair · gemini-2.0-flash

    originally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Evangelio
    -0.65
     виправивши
    -0.52
    cloudfront
    -0.51
     AssemblyTitle
    -0.47
    WebpackPlugin
    -0.47
    wai
    -0.47
     combinatie
    -0.46
     Wiktionnaire
    -0.45
     säll
    -0.45
    icol
    -0.44
    POSITIVE LOGITS
    undra
    0.65
    didSet
    0.57
     ProtoMessage
    0.57
    :✨
    0.56
    ClientSize
    0.55
    gulier
    0.54
     calendriers
    0.53
    itudinal
    0.53
     alert
    0.52
    PERTIES
    0.52
    Activations Density 0.589%

    No Known Activations