© 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. 12791
    Prev
    Next
    INDEX
    Explanations

    mentions of authors in relation to the works they authored

    oai_token-act-pair · gemini-2.0-flash

    words indicating relationships and connections

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

    of

    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
     aéreo
    -0.70
     vocale
    -0.63
     cardiaque
    -0.62
     Statewide
    -0.61
     orgánico
    -0.61
    Viited
    -0.60
     inéd
    -0.60
     fotográfico
    -0.60
     GoogleFonts
    -0.60
    risten
    -0.59
    POSITIVE LOGITS
     mergeFrom
    0.53
     utafitiHapana
    0.53
     ویکی‌پدیا
    0.52
     this
    0.51
    MemoryWarning
    0.51
     kasarigan
    0.50
    CodeAttribute
    0.48
     its
    0.48
     humanity
    0.47
     strongest
    0.47
    Activations Density 1.522%

    No Known Activations