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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12594
    Prev
    Next
    INDEX
    Explanations

    mentions of things "working fine" in code or technical contexts

    oai_token-act-pair · gemini-2.0-flash

    fine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ta
    -0.47
    KeyName
    -0.45
    elif
    -0.42
    ers
    -0.42
    วด
    -0.42
    ceğine
    -0.41
    chanical
    -0.41
    acağına
    -0.41
    st
    -0.40
    انگلیسی
    -0.40
    POSITIVE LOGITS
    MigrationBuilder
    1.03
     nakalista
    0.93
     تضيفلها
    0.93
     CreateTagHelper
    0.91
    Personensuche
    0.85
    IUrlHelper
    0.80
    存于互联网档案馆
    0.78
    
    0.78
     Савезне
    0.77
    twimg
    0.76
    Activations Density 4.929%

    No Known Activations