© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14647
    Prev
    Next
    INDEX
    Explanations

    the word "check" sometimes associated with hyphenated words or "to"

    oai_token-act-pair · gemini-2.0-flash

    check

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     check
    -2.58
    check
    -2.38
     Check
    -2.34
    Check
    -2.27
     checks
    -2.25
     checking
    -2.19
     CHECK
    -2.16
     Checking
    -2.14
     checked
    -2.13
     Checks
    -2.11
    POSITIVE LOGITS
     bezeichneter
    0.71
     Infórmanos
    0.68
     jScrollPane
    0.66
     Савезне
    0.60
     виправивши
    0.59
    
    0.54
     versteht
    0.50
    AnchorStyles
    0.50
     незавершена
    0.49
    InjectAttribute
    0.48
    Activations Density 1.551%

    No Known Activations