© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1086
    Prev
    Next
    INDEX
    Explanations

    text requesting monetary contributions or other kinds of donations.

    oai_token-act-pair · gemini-2.0-flash

    Legal/official documentation

    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
    atimes
    -0.48
    vun
    -0.45
     getItemId
    -0.44
     bare
    -0.43
     <
    -0.43
    ミニ
    -0.43
    interopRequire
    -0.43
    一股
    -0.42
    redd
    -0.41
    sep
    -0.41
    POSITIVE LOGITS
     وتسجيلات
    0.68
     Efq
    0.65
    ínű
    0.65
     raiſ
    0.64
     nahilalakip
    0.64
     myſelf
    0.62
    ſelves
    0.61
     Middles
    0.59
    TagHelper
    0.59
     Enoch
    0.58
    Activations Density 0.767%

    No Known Activations