© 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. 2506
    Prev
    Next
    INDEX
    Explanations

    question words like "how," "what," and "why"

    oai_token-act-pair · gemini-2.0-flash

    how

    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
    How
    -1.63
     How
    -1.59
     how
    -1.59
    how
    -1.48
    HOW
    -1.22
     HOW
    -1.22
     Cómo
    -0.94
     كيف
    -0.93
    Hvordan
    -0.93
     कैसे
    -0.92
    POSITIVE LOGITS
    \}\\
    0.66
    TestingModule
    0.52
    tojas
    0.49
    oroz
    0.48
    saga
    0.45
    dasarkan
    0.43
    CATCH
    0.42
    ++++++++++++++++
    0.42
    velse
    0.42
     Vars
    0.42
    Activations Density 4.660%

    No Known Activations