© 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. 13532
    Prev
    Next
    INDEX
    Explanations

    the word "the" but sometimes it finds "a", "Mer", numbers, inventions, or prototype creation

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb 'work'

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

    work

    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
    UnknownFieldSet
    -0.54
    rój
    -0.51
     Normdatei
    -0.47
    Спасылкі
    -0.45
     MonoBehaviour
    -0.45
    nonatomic
    -0.44
     rechange
    -0.44
    await
    -0.43
    wati
    -0.43
    outState
    -0.43
    POSITIVE LOGITS
     working
    3.47
    working
    3.14
    Working
    3.02
     Working
    2.98
     WORKING
    2.95
    WORKING
    2.81
     worked
    2.06
     trabajando
    1.85
    worked
    1.83
     works
    1.79
    Activations Density 2.992%

    No Known Activations