© 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. 7322
    Prev
    Next
    INDEX
    Explanations

    documentation links and code instructions

    oai_token-act-pair · gemini-2.0-flash

    programming and coding terms

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

    Code or documentation

    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
     HasFactory
    -0.58
    writeField
    -0.54
    principalColumn
    -0.53
     posi
    -0.47
    aris
    -0.46
    EndGlobalSection
    -0.46
     Dietz
    -0.46
     www
    -0.46
     EconPapers
    -0.46
     runs
    -0.44
    POSITIVE LOGITS
     ExecuteAsync
    0.69
    AsUp
    0.63
    ImageContext
    0.62
    nologue
    0.61
    はじめに
    0.59
    
    0.59
    ModelBuilder
    0.57
    WriteTagHelper
    0.55
     snippetHide
    0.55
    HasBeenSet
    0.53
    Activations Density 3.732%

    No Known Activations