© 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. 13346
    Prev
    Next
    INDEX
    Explanations

    words associated with development and design, or words ending in "phase" or "stage"

    oai_token-act-pair · gemini-2.0-flash

    phase/stage

    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
     utafitiHapana
    -0.65
     dimentic
    -0.53
    zzá
    -0.53
    Ụ
    -0.52
     haja
    -0.52
    юрпри
    -0.51
    Snippet
    -0.50
    MethodManager
    -0.50
     acrylique
    -0.50
    zaamheid
    -0.49
    POSITIVE LOGITS
     phase
    2.66
    phase
    2.22
     Phase
    2.09
    Phase
    1.94
     phases
    1.91
     stage
    1.90
     PHASE
    1.86
    PHASE
    1.70
     fase
    1.67
    phases
    1.62
    Activations Density 3.550%

    No Known Activations