© 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. 15697
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is asking for assistance

    oai_token-act-pair · gemini-2.0-flash

    asking for help

    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
     BorderSide
    -0.98
     bezeichneter
    -0.91
    twimg
    -0.91
     initComponents
    -0.91
     onAnimation
    -0.90
     дописавши
    -0.87
     oprot
    -0.86
    queryInterface
    -0.83
     Efq
    -0.83
    mybatisplus
    -0.81
    POSITIVE LOGITS
     most
    0.49
     Most
    0.40
    acki
    0.38
    мула
    0.36
     app
    0.35
    нт
    0.35
    nthetic
    0.35
     int
    0.35
     ma
    0.34
    llo
    0.33
    Activations Density 1.222%

    No Known Activations