© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13459
    Prev
    Next
    INDEX
    Explanations

    words that start with "ch" or contain "tch", or the substring "ash"

    oai_token-act-pair · gemini-2.0-flash

    technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    DeleteBehavior
    -0.61
     ComVisible
    -0.58
    OrNil
    -0.58
    bouts
    -0.52
    PRNewswire
    -0.50
     оригіналу
    -0.49
    jstor
    -0.48
     CreateTagHelper
    -0.46
    zzleHttp
    -0.45
     emporio
    -0.44
    POSITIVE LOGITS
    ,:);
    0.56
    ParallelGroup
    0.55
     EconPapers
    0.54
    LEncoder
    0.54
    ')")
    0.51
    Зноскі
    0.51
    senior
    0.51
    θος
    0.49
    íncia
    0.49
    haden
    0.49
    Activations Density 0.387%

    No Known Activations