© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12019
    Prev
    Next
    INDEX
    Explanations

    the word "themselves"

    oai_token-act-pair · gemini-2.0-flash

    themselves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     themſelves
    -1.10
     itſelf
    -0.94
     themselves
    -0.93
     ſind
    -0.84
     Efq
    -0.80
     himſelf
    -0.79
     becauſe
    -0.77
     uſed
    -0.77
    themselves
    -0.77
    addCriterion
    -0.75
    POSITIVE LOGITS
    MethodManager
    0.58
     समीक्षाएं
    0.57
    tanleria
    0.55
    Whilst
    0.54
    jfree
    0.53
     بتاريخ
    0.52
    mybatisplus
    0.52
     whilst
    0.52
     Little
    0.50
     Whilst
    0.50
    Activations Density 0.243%

    No Known Activations