© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14481
    Prev
    Next
    INDEX
    Explanations

    the letters "ou" inside of a word

    oai_token-act-pair · gemini-2.0-flash

    tokens containing 'ou' or similar letter patterns

    np_token-act-pair-logits · gpt-4o-mini
    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
    +#+#
    -0.81
    VIAF
    -0.72
    forChild
    -0.68
    TagMode
    -0.65
    Искәрмәләр
    -0.63
     onCreateView
    -0.61
    inerja
    -0.58
    astify
    -0.57
     CommandType
    -0.57
     @}
    -0.56
    POSITIVE LOGITS
    AntiForgeryToken
    0.62
    AutoField
    0.57
    o
    0.51
     ň
    0.48
    möglichen
    0.46
     chng
    0.44
    NewUrlParser
    0.43
    اقرأ
    0.43
     veuillez
    0.42
    SharedDtor
    0.42
    Activations Density 0.583%

    No Known Activations