© 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. 13296
    Prev
    Next
    INDEX
    Explanations

    a mix of terms related to tradition and innovation, as well as programming and general quantifiers/pronouns

    oai_token-act-pair · gemini-2.0-flash

    multi-lingual or mixed-language terms

    np_token-act-pair-logits · gpt-4o-mini
    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
     raiſ
    -0.78
     Diſ
    -0.71
     Efq
    -0.69
     Monfieur
    -0.69
     Anſ
    -0.65
     Cæsar
    -0.63
     Eſ
    -0.62
     Wikimédia
    -0.60
     whoſe
    -0.60
     faſt
    -0.60
    POSITIVE LOGITS
     autorytatywna
    0.73
     चीज़ों
    0.60
     وتسجيلات
    0.59
    MLLoader
    0.54
     fieldNum
    0.54
     صوتيه
    0.53
    PagerAdapter
    0.53
    yntaxException
    0.52
    Архівовано
    0.52
    AndEndTag
    0.51
    Activations Density 0.813%

    No Known Activations