© 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. 9820
    Prev
    Next
    INDEX
    Explanations

    the letter "A" followed by a hyphen or a forward slash

    oai_token-act-pair · gemini-2.0-flash

    terms related to the letter 'A'

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

    codes and abbreviations

    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
     "..\..\..\
    -0.73
    expandindo
    -0.73
     "..\..\
    -0.69
     AssemblyCompany
    -0.66
    mergeFrom
    -0.62
    addGap
    -0.61
    yntaxException
    -0.60
     esternos
    -0.60
    Personensuche
    -0.56
    PropertyChanging
    -0.55
    POSITIVE LOGITS
     Савезне
    0.55
     bParam
    0.47
     Clone
    0.44
    pedia
    0.43
     consultato
    0.43
    ียน
    0.42
     corners
    0.42
    Rolls
    0.42
     Wikidata
    0.41
     Sera
    0.41
    Activations Density 0.603%

    No Known Activations