© 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. 13473
    Prev
    Next
    INDEX
    Explanations

    code elements like curly braces, parentheses, keywords, and string literals

    oai_token-act-pair · gemini-2.0-flash

    Parentheses

    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
     “
    -0.27
    um
    -0.26
     ‘
    -0.23
      
    -0.21
    uz
    -0.20
    <strong>
    -0.19
     A
    -0.18
     â
    -0.18
     …
    -0.18
    ü
    -0.18
    POSITIVE LOGITS
     myſelf
    1.46
     Efq
    1.45
     itſelf
    1.43
     Monfieur
    1.42
     Theſe
    1.38
     himſelf
    1.33
     Jefus
    1.28
     themſelves
    1.27
     ſind
    1.26
     ſeveral
    1.22
    Activations Density 11.033%

    No Known Activations