© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5756
    Prev
    Next
    INDEX
    Explanations

    references to amounts or quantities

    oai_token-act-pair · gemini-2.0-flash

    Data, measurements, statistics

    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
     levels
    -1.19
     Levels
    -1.00
    levels
    -0.96
     speeds
    -0.88
     LEVELS
    -0.87
     rates
    -0.85
    Levels
    -0.84
     volumes
    -0.84
     densities
    -0.81
     numbers
    -0.80
    POSITIVE LOGITS
    AddTagHelper
    0.91
     يتيمه
    0.82
    脚注の使い方
    0.79
    ArgsConstructor
    0.73
    RegressionTest
    0.69
     utafitiHapana
    0.69
     tartalomajánló
    0.69
     تضيفلها
    0.66
    uxxxx
    0.66
    ьаж
    0.65
    Activations Density 2.232%

    No Known Activations