© 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. 4403
    Prev
    Next
    INDEX
    Explanations

    scientific texts, especially those describing simulations, and focusing on time, rate, and conditions

    oai_token-act-pair · gemini-2.0-flash

    terms related to scientific concepts or variables

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

    at

    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
    ⓧ
    -0.71
    ISupport
    -0.67
    httphttps
    -0.58
    RenderAtEndOf
    -0.58
     bénévoles
    -0.57
    ivably
    -0.56
     russes
    -0.54
    AnimationsModule
    -0.52
     écl
    -0.52
     honom
    -0.52
    POSITIVE LOGITS
     constant
    0.59
    ρίζ
    0.58
    cri
    0.57
    بوابة
    0.54
     particular
    0.53
     each
    0.52
     days
    0.52
     gig
    0.51
     interface
    0.50
     temperatures
    0.50
    Activations Density 10.145%

    No Known Activations