© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5330
    Prev
    Next
    INDEX
    Explanations

    words that are used to express necessity or ability

    oai_token-act-pair · gemini-2.0-flash

    tokens with unusual characters or symbols

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

    could

    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
    viewDidLoad
    -0.69
    ]=>
    -0.65
     مشين
    -0.62
    avoit
    -0.59
    OrBuilder
    -0.59
     poursuite
    -0.57
     CGPoint
    -0.57
    __*/
    -0.55
     uLocal
    -0.54
     &___
    -0.54
    POSITIVE LOGITS
    ftagPool
    0.65
     chips
    0.49
    ểm
    0.49
    melde
    0.47
     regra
    0.45
     pip
    0.45
     Timor
    0.45
    尚
    0.45
     compro
    0.45
    :✨
    0.44
    Activations Density 1.438%

    No Known Activations