© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1721
    Prev
    Next
    INDEX
    Explanations

    a mix of numerical codes, abbreviations, last names and the letter H

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Efq
    -1.05
     myſelf
    -0.90
     ſeveral
    -0.88
     Houſe
    -0.82
     Theſe
    -0.82
    ſelves
    -0.82
    ſelf
    -0.82
     Diſ
    -0.80
     Eſ
    -0.80
     houſe
    -0.79
    POSITIVE LOGITS
      
    0.39
    ритори
    0.38
    არი
    0.38
     joaat
    0.36
    </b>
    0.35
    acan
    0.34
     الدولى
    0.34
    toUpperCase
    0.34
     autorytatywna
    0.33
    </
    0.33
    Activations Density 0.056%

    No Known Activations