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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7742
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to establishing the objective of a study or experiment

    oai_token-act-pair · gemini-2.0-flash

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Goals
    -0.72
     goals
    -0.72
     purpoſe
    -0.70
    Goals
    -0.70
    goals
    -0.68
     Majefty
    -0.66
     ſtate
    -0.66
    ſelves
    -0.66
    ſelf
    -0.65
     goal
    -0.65
    POSITIVE LOGITS
    AndEndTag
    0.54
     noten
    0.51
    +#+#
    0.50
    ViewImports
    0.50
     jScrollPane
    0.49
    knapp
    0.48
     ostavi
    0.47
    "}")
    0.47
    fjspx
    0.46
    kunde
    0.45
    Activations Density 9.533%

    No Known Activations