© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13409
    Prev
    Next
    INDEX
    Explanations

    C preprocessor directives defining bit fields

    oai_token-act-pair · gemini-2.0-flash

    code definitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     pleaſure
    -0.88
     perſon
    -0.87
     himſelf
    -0.87
     ſmall
    -0.86
     bershka
    -0.86
     themſelves
    -0.85
     raiſ
    -0.85
     perfons
    -0.82
     preſent
    -0.82
     itſelf
    -0.82
    POSITIVE LOGITS
     u
    0.54
     []
    0.53
     q
    0.51
     ()
    0.50
     sz
    0.48
     df
    0.47
     (
    0.47
     NULL
    0.46
     e
    0.46
     DB
    0.46
    Activations Density 14.519%

    No Known Activations