© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14001
    Prev
    Next
    INDEX
    Explanations

    references to weather disasters and their effects.

    oai_token-act-pair · gemini-2.0-flash

    the word "natural"

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

    natural

    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
    findpost
    -0.57
     Normdatei
    -0.49
    uft
    -0.47
    ophytes
    -0.47
    muebles
    -0.46
     latex
    -0.45
     plastico
    -0.45
     المعرف
    -0.44
    timewa
    -0.44
    UnusedPrivate
    -0.44
    POSITIVE LOGITS
     natural
    0.71
    出版年
    0.68
     force
    0.62
    migrationBuilder
    0.62
    InstanceState
    0.61
     natürlichen
    0.61
     Natural
    0.60
     natuur
    0.60
     naturales
    0.60
    natural
    0.59
    Activations Density 2.164%

    No Known Activations