© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10350
    Prev
    Next
    INDEX
    Explanations

    numerical values or measurements

    oai_token-act-pair · gemini-2.0-flash

    data extraction

    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
     less
    -0.55
     thousands
    -0.53
    ={()=>
    -0.51
     tens
    -0.50
     roughly
    -0.49
     hundreds
    -0.48
     approximately
    -0.47
    يميديا
    -0.47
    med
    -0.46
     (~
    -0.46
    POSITIVE LOGITS
    SourceChecksum
    0.63
    PositiveButton
    0.61
    TagMode
    0.61
     MonoBehaviour
    0.60
    ̍t
    0.59
     Normdatei
    0.59
     ElementRef
    0.57
    BeginContext
    0.57
     BorderRadius
    0.55
    fjspx
    0.55
    Activations Density 4.554%

    No Known Activations