© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11857
    Prev
    Next
    INDEX
    Explanations

    dates, especially years

    oai_token-act-pair · gemini-2.0-flash

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     pinulongan
    -0.73
    MigrationBuilder
    -0.71
     بيها
    -0.71
    zzleHttp
    -0.66
    MemoryWarning
    -0.66
    IsContent
    -0.63
    ंदीखरीदारी
    -0.63
     AssemblyCulture
    -0.62
    发表于
    -0.62
     viewDidLoad
    -0.61
    POSITIVE LOGITS
     Abt
    0.61
    ungkinan
    0.59
     contextLoads
    0.56
     NLA
    0.54
    ATN
    0.53
     Sabina
    0.52
    MsgBox
    0.50
     PHA
    0.49
     APT
    0.48
     Kalk
    0.48
    Activations Density 0.291%

    No Known Activations