© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5380
    Prev
    Next
    INDEX
    Explanations

    references to actions or events happening in the past

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'work'

    np_token-act-pair-logits · gpt-4o-mini

    working, work

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    henswürdigkeiten
    -0.65
    DoubleQuotes
    -0.63
     referenties
    -0.59
    NewUrlParser
    -0.55
     NavController
    -0.54
    oprecip
    -0.53
     Normdatei
    -0.53
     sumpay
    -0.52
     Maharaj
    -0.52
    AntiForgeryToken
    -0.52
    POSITIVE LOGITS
     working
    2.39
    working
    2.19
     work
    2.13
    Working
    2.09
     worked
    2.09
     Working
    2.08
     WORKING
    1.91
    work
    1.90
    WORKING
    1.89
     works
    1.88
    Activations Density 2.515%

    No Known Activations