© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12316
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to food or agriculture

    oai_token-act-pair · gemini-2.0-flash

    quantity/amount

    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
    AppCompat
    -0.64
    Tracce
    -0.59
    setVerticalGroup
    -0.55
     Alcott
    -0.54
     IconData
    -0.52
     Савезне
    -0.52
     ParseException
    -0.49
     سكانية
    -0.49
     PHPUnit
    -0.48
     gọn
    -0.47
    POSITIVE LOGITS
    MessageInfo
    0.68
     case
    0.58
     barrel
    0.56
    djangoproject
    0.55
    exitRule
    0.55
     barrels
    0.54
    ThroughAttribute
    0.54
    featureID
    0.53
    case
    0.53
     cases
    0.53
    Activations Density 1.418%

    No Known Activations