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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14447
    Prev
    Next
    INDEX
    Explanations

    years, especially those beginning with "191"

    oai_token-act-pair · gemini-2.0-flash

    food related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     klap
    -0.54
     Públicas
    -0.52
     tongs
    -0.52
     Independiente
    -0.52
     Managua
    -0.50
     racc
    -0.49
     Cortés
    -0.48
     hilar
    -0.47
     postale
    -0.47
    SharedCtor
    -0.47
    POSITIVE LOGITS
     Meksiku
    0.64
    webElementGuid
    0.57
     light
    0.57
    gameserver
    0.55
     Rij
    0.54
    afficheront
    0.52
    wixt
    0.52
    GOTREF
    0.51
    migrationBuilder
    0.51
     tartalomajánló
    0.49
    Activations Density 0.549%

    No Known Activations