© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2966
    Prev
    Next
    INDEX
    Explanations

    words related to decisions, particularly those by authority figures.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'make'

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

    make

    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
    parsedMessage
    -0.73
     sumpay
    -0.67
    IndentedString
    -0.63
     JpaRepository
    -0.59
    InitVars
    -0.58
     ProtoMessage
    -0.57
    ArrowToggle
    -0.56
    RegressionTest
    -0.56
    NameInMap
    -0.56
    الحياه
    -0.56
    POSITIVE LOGITS
     made
    2.67
    made
    2.39
     make
    2.34
     Made
    2.34
    Made
    2.33
     MADE
    2.20
    make
    2.19
     Make
    2.17
    Make
    2.13
     makes
    2.06
    Activations Density 5.554%

    No Known Activations