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. 1001
    Prev
    Next
    INDEX
    Explanations

    legal language related to sexual crimes, especially against children

    oai_token-act-pair · gemini-2.0-flash

    sexual abuse

    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
     InputDecoration
    -0.80
     dAtA
    -0.74
    contentLoaded
    -0.69
    ISupport
    -0.68
    RegressionTest
    -0.67
    AccessorTable
    -0.65
    IUrlHelper
    -0.65
     speedo
    -0.65
     fathoms
    -0.64
    ReusableCell
    -0.64
    POSITIVE LOGITS
    posten
    0.50
     Licht
    0.43
     care
    0.43
     prévention
    0.42
     materiales
    0.42
    jina
    0.42
     Whit
    0.42
     Mann
    0.42
     légiti
    0.41
    хь
    0.41
    Activations Density 13.324%

    No Known Activations