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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13497
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with the topics of race, voting, labor, and sexual assault

    oai_token-act-pair · gemini-2.0-flash

    Politics and exploitation

    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
    🦯
    -0.49
     dipinto
    -0.46
    pected
    -0.45
    Footnotes
    -0.44
     Masyarakat
    -0.44
     coscienza
    -0.44
    IMPORTED
    -0.43
    associazione
    -0.42
    couvrez
    -0.42
    pero
    -0.42
    POSITIVE LOGITS
     pinulongan
    0.79
    SharedCtor
    0.77
    expandindo
    0.75
     незавершена
    0.72
    AutoScaleMode
    0.71
    دانشنامهٔ
    0.71
     utafitiHapana
    0.71
    Jeografia
    0.70
    webElementGuid
    0.69
     "..\..\..\
    0.69
    Activations Density 2.366%

    No Known Activations