© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13430
    Prev
    Next
    INDEX
    Explanations

    words that appear to be non-English verbs or words ending in "s" with emphasis on languages other than English

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Efq
    -1.34
     Majefty
    -1.33
     Anſ
    -1.26
     Monfieur
    -1.25
     itſelf
    -1.23
     myſelf
    -1.23
     ſeveral
    -1.20
     Theſe
    -1.19
     Conſ
    -1.17
     Reſ
    -1.16
    POSITIVE LOGITS
    ↵↵
    0.59
     "
    0.55
     
    0.53
     lo
    0.49
     '
    0.49
     “
    0.46
     sub
    0.46
    <eos>
    0.43
     c
    0.43
     N
    0.42
    Activations Density 4.511%

    No Known Activations