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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14336
    Prev
    Next
    INDEX
    Explanations

    names of places in Vietnam

    oai_token-act-pair · gemini-2.0-flash

    Vietnam locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     purpoſe
    -0.68
     fubject
    -0.66
     itſelf
    -0.63
     cauſe
    -0.60
     Efq
    -0.59
     uſe
    -0.59
     uſ
    -0.59
     perſon
    -0.58
     pleaſure
    -0.58
     Jefus
    -0.57
    POSITIVE LOGITS
    Hozzáférés
    0.61
    DCC
    0.57
    chond
    0.57
    StoryboardSegue
    0.57
    מעות
    0.56
    Tazama
    0.55
    visiae
    0.55
    lishes
    0.54
    Revenir
    0.52
    olescence
    0.52
    Activations Density 0.245%

    No Known Activations