© 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. 11943
    Prev
    Next
    INDEX
    Explanations

    code and code-related syntax

    oai_token-act-pair · gemini-2.0-flash

    code/mathematical expressions

    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
    InjectAttribute
    -0.82
     ModelExpression
    -0.81
    BeginInit
    -0.78
    PerformLayout
    -0.75
     kaarangay
    -0.75
    EndInit
    -0.73
    StoryboardSegue
    -0.71
    зулта
    -0.71
    帖最后由
    -0.70
    KommentareTeilen
    -0.69
    POSITIVE LOGITS
    mag
    0.49
    bez
    0.46
     tayo
    0.45
     mag
    0.45
    d
    0.44
    ichern
    0.43
     Tutte
    0.43
     marginal
    0.42
    ốt
    0.41
     cilvē
    0.41
    Activations Density 29.962%

    No Known Activations