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. 817
    Prev
    Next
    INDEX
    Explanations

    text about human rights violations and political protests in specific countries.

    oai_token-act-pair · gemini-2.0-flash

    rights

    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
     tartalomajánló
    -0.75
     EconPapers
    -0.69
    ControllerTest
    -0.65
    djangoproject
    -0.64
    ControllerAdvice
    -0.63
    AutoScale
    -0.62
    __.__
    -0.61
     <=",
    -0.60
     morire
    -0.60
    ↹
    -0.60
    POSITIVE LOGITS
     Eintrag
    0.46
     publiés
    0.41
     sign
    0.41
    postmedia
    0.41
     Drapeau
    0.40
     podpis
    0.40
     comunidad
    0.39
     signing
    0.39
    ופה
    0.39
    CDATA
    0.39
    Activations Density 38.157%

    No Known Activations