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. 14467
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and places

    oai_token-act-pair · gemini-2.0-flash

    Names of people

    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
     herself
    -0.91
    herself
    -0.88
     defaultstate
    -0.82
    verwijspagina
    -0.82
    AsUp
    -0.78
     firebaseConfig
    -0.73
     SwitchCompat
    -0.71
    Personensuche
    -0.69
     resourceCulture
    -0.69
     she
    -0.68
    POSITIVE LOGITS
    WithMany
    0.53
    Deskripsi
    0.50
     intptr
    0.45
    vele
    0.41
    Portail
    0.41
    otte
    0.39
    anske
    0.38
    otrophic
    0.37
    ann
    0.37
     BoxDecoration
    0.37
    Activations Density 0.621%

    No Known Activations