© 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. 3496
    Prev
    Next
    INDEX
    Explanations

    articles about current events and their surrounding context.

    oai_token-act-pair · gemini-2.0-flash

    programming language keywords or function names

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

    the

    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
     kasarigan
    -0.70
     OnInit
    -0.51
    Vedi
    -0.48
    verifyException
    -0.47
    timewa
    -0.47
    häuse
    -0.47
     Load
    -0.46
    BeginContext
    -0.45
    #+#
    -0.44
    MessageWindow
    -0.44
    POSITIVE LOGITS
    glVertex
    0.67
     surla
    0.63
    ">//
    0.63
    UnsafeEnabled
    0.60
    Према
    0.55
     redé
    0.52
    phazard
    0.52
    Skocz
    0.52
    PyExc
    0.52
     country
    0.51
    Activations Density 1.239%

    No Known Activations