© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6741
    Prev
    Next
    INDEX
    Explanations

    cases where a number is present "out of" another number

    oai_token-act-pair · gemini-2.0-flash

    terms related to conclusions and references

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

    of/in

    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
    tagHelperRunner
    -1.03
     disambiguazione
    -0.85
    исленность
    -0.79
    httphttps
    -0.77
    PMailer
    -0.75
     للمعارف
    -0.73
    Clik
    -0.68
    addGap
    -0.67
    igshid
    -0.66
    FormTagHelper
    -0.66
    POSITIVE LOGITS
    Conclusão
    0.52
    Formazione
    0.43
     henvisninger
    0.43
    Referensi
    0.42
     discharge
    0.42
     conclusion
    0.42
     CONCLUSION
    0.42
    impianto
    0.41
     partida
    0.40
     Púb
    0.40
    Activations Density 4.928%

    No Known Activations