Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 791
    Prev
    Next
    INDEX
    Explanations

    text related to machine learning training processes and data analysis

    oai_token-act-pair · gemini-2.0-flash

    training

    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
     IndexPath
    -0.53
    principalTable
    -0.47
     inhibition
    -0.47
    Geplaatst
    -0.47
    monials
    -0.47
    oltán
    -0.46
    NewReader
    -0.46
     réessayer
    -0.46
    Tried
    -0.46
    bobox
    -0.44
    POSITIVE LOGITS
    AnchorStyles
    0.65
    Suara
    0.65
     obiec
    0.63
     يتيمه
    0.60
    AutoScaleMode
    0.60
    ⓘ
    0.59
    WindowConstants
    0.59
     bakgrund
    0.58
    study
    0.58
    getMenuInflater
    0.56
    Activations Density 1.647%

    No Known Activations