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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4868
    Prev
    Next
    INDEX
    Explanations

    currency amounts and monetary terms

    oai_token-act-pair · gemini-2.0-flash

    currency amounts and financial figures

    np_token-act-pair-logits · gpt-4o-mini

    currency amounts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     GenerationType
    -0.94
    StoryboardSegue
    -0.84
     تضيفلها
    -0.79
    ByVersion
    -0.79
     TestBed
    -0.77
     propOrder
    -0.77
    RegressionTest
    -0.75
    wpi
    -0.73
    LookAnd
    -0.72
    GHIJKLM
    -0.71
    POSITIVE LOGITS
    ufige
    0.48
    Pranala
    0.45
    ].(
    0.44
    bership
    0.41
    __]
    0.38
     kira
    0.37
    ]")]
    0.36
     yılında
    0.36
     winkel
    0.35
    SplashScreen
    0.35
    Activations Density 2.933%

    No Known Activations