© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2662
    Prev
    Next
    INDEX
    Explanations

    phrases asserting a task can be done easily or directly

    oai_token-act-pair · gemini-2.0-flash

    Easiness or simplicity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     easily
    -2.02
    easily
    -1.88
     easy
    -1.87
     easier
    -1.77
     ease
    -1.73
     Easily
    -1.72
    easy
    -1.72
    Easy
    -1.61
    Easily
    -1.58
     eas
    -1.55
    POSITIVE LOGITS
     kaynağından
    0.50
    lances
    0.49
     tartalomajánló
    0.49
    Puss
    0.49
     gepubliceerd
    0.48
    PullParser
    0.47
     dalamnya
    0.45
    ControllerAdvice
    0.45
    currentThread
    0.43
    不已
    0.43
    Activations Density 2.442%

    No Known Activations