© 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. 11633
    Prev
    Next
    INDEX
    Explanations

    the word 'state' preceded by the word 'to'

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming-related concepts

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

    code

    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
     tap
    -0.43
     number
    -0.40
    #![
    -0.40
    ><!--
    -0.39
    olio
    -0.37
     MS
    -0.36
     Meksiku
    -0.36
     IconData
    -0.36
    IGATION
    -0.36
    SPJ
    -0.36
    POSITIVE LOGITS
     متعلقه
    0.88
    hyrchwyd
    0.69
     gynhyrchwyd
    0.68
    versy
    0.64
    URLException
    0.61
     convergence
    0.60
     createStore
    0.60
    RetentionPolicy
    0.59
     gọn
    0.59
     HttpNotFound
    0.58
    Activations Density 6.776%

    No Known Activations