© 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. 7371
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that function as adverbs or descriptors involving the concept of comparison

    oai_token-act-pair · gemini-2.0-flash

    the word 'as' in multiple languages

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

    "as" in other languages

    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
    enderror
    -0.80
    évaluateur
    -0.77
    Personendaten
    -0.73
     disambiguazione
    -0.71
     AssemblyCompany
    -0.69
    NamedQueries
    -0.69
    oredCriteria
    -0.68
    脚注の使い方
    -0.68
    AutoScale
    -0.66
     виправивши
    -0.65
    POSITIVE LOGITS
     as
    2.67
     sebagai
    1.66
     как
    1.38
    作为
    1.34
    as
    1.25
     як
    1.25
    作為
    1.23
     као
    1.23
     ως
    1.21
     jako
    1.20
    Activations Density 2.940%

    No Known Activations