© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4015
    Prev
    Next
    INDEX
    Explanations

    words ending in "ment," particularly as they relate to legal or bureaucratic contexts

    oai_token-act-pair · gemini-2.0-flash

    words related to "men."

    np_token-act-pair-logits · gpt-4o-mini

    Contains "men"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    alba
    -0.51
    Tikang
    -0.48
     QtWidgets
    -0.45
    erover
    -0.44
     [.
    -0.44
     pinulongan
    -0.44
    ths
    -0.44
    viewDidLoad
    -0.43
     Deber
    -0.43
     Duca
    -0.42
    POSITIVE LOGITS
     men
    0.96
    men
    0.96
    mens
    0.88
    Men
    0.86
    Ment
    0.85
     Men
    0.83
    emen
    0.82
     ment
    0.81
    mental
    0.80
    MEN
    0.79
    Activations Density 1.361%

    No Known Activations