© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13980
    Prev
    Next
    INDEX
    Explanations

    LaTeX, C++, and Java code

    oai_token-act-pair · gemini-2.0-flash

    Capital letters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     itſelf
    -2.88
     myſelf
    -2.73
     pleaſure
    -2.53
     Monfieur
    -2.53
     Reſ
    -2.52
     Efq
    -2.52
    ſelf
    -2.47
     Anſ
    -2.45
    ſelves
    -2.45
     Jefus
    -2.44
    POSITIVE LOGITS
     I
    1.63
     
    1.50
     C
    1.48
     A
    1.47
     P
    1.43
     S
    1.42
     B
    1.41
     F
    1.41
     f
    1.41
     M
    1.41
    Activations Density 7.175%

    No Known Activations