© 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. 13381
    Prev
    Next
    INDEX
    Explanations

    arxiv and PhysRev citations, field theory and numbers with exponents

    oai_token-act-pair · gemini-2.0-flash

    technical terms and data structure references

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

    Code and unusual words

    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
    AccessorTable
    -0.61
    apimachinery
    -0.52
     nhau
    -0.52
    bitol
    -0.51
     access
    -0.51
     Na
    -0.50
    access
    -0.49
    GeneratedMessage
    -0.49
     mergeFrom
    -0.47
     Access
    -0.47
    POSITIVE LOGITS
    styleUrls
    0.69
     linkovi
    0.59
    UrlEncoded
    0.59
    NUMX
    0.58
     getItemId
    0.57
     Offisielt
    0.57
    WriteBarrier
    0.57
    AnimationFrame
    0.54
    Skocz
    0.53
    tvguidetime
    0.53
    Activations Density 5.892%

    No Known Activations