© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10676
    Prev
    Next
    INDEX
    Explanations

    sequences of words that indicate failure of a plan or measure

    oai_token-act-pair · gemini-2.0-flash

    failure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     <=",
    -0.55
    BoxShadow
    -0.50
     noires
    -0.47
     Tempt
    -0.46
    shadowOffset
    -0.46
    ngx
    -0.45
     Polskiego
    -0.44
     soigne
    -0.43
     nghi
    -0.43
    phrine
    -0.43
    POSITIVE LOGITS
     failure
    1.48
     fail
    1.48
     failed
    1.46
     failing
    1.42
     fails
    1.41
     Failure
    1.29
     failures
    1.28
    failure
    1.25
     Fail
    1.23
    fail
    1.23
    Activations Density 1.849%

    No Known Activations