© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12227
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating problems or impairments

    oai_token-act-pair · gemini-2.0-flash

    problems/impairments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    MessageTagHelper
    -0.62
     effect
    -0.59
    verifyException
    -0.58
     issue
    -0.54
    Effect
    -0.51
     Effect
    -0.51
    ControllerAdvice
    -0.51
    RTLD
    -0.50
     problem
    -0.49
     difference
    -0.48
    POSITIVE LOGITS
    
    0.73
    setVerticalGroup
    0.65
     surla
    0.62
    konomi
    0.59
    initWithFrame
    0.58
    seamnă
    0.58
    новништво
    0.57
    CPtr
    0.54
     OFDb
    0.54
     utafitiHapana
    0.52
    Activations Density 8.931%

    No Known Activations