© 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. 10752
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs or derivations, especially citations of previous work and numbered equations

    oai_token-act-pair · gemini-2.0-flash

    technical terms or references to programming concepts

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

    Equations and references

    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
    Datuak
    -0.90
     насељу
    -0.68
     autorytatywna
    -0.65
    Autoritní
    -0.65
    okovic
    -0.60
    buttonBar
    -0.60
    AnchorTagHelper
    -0.59
    COUVER
    -0.58
    StoryboardSegue
    -0.56
     HasFactory
    -0.56
    POSITIVE LOGITS
    ✨:
    0.50
    yntaxException
    0.49
    ItemSelected
    0.48
     Krakowie
    0.46
     hold
    0.46
    Spaces
    0.45
     HomeComponent
    0.45
    SPACE
    0.45
    bis
    0.44
    ArgumentParser
    0.44
    Activations Density 6.409%

    No Known Activations