© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9803
    Prev
    Next
    INDEX
    Explanations

    the string "id" or the word "mind"

    oai_token-act-pair · gemini-2.0-flash

    code identifiers

    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
    Negative Logits
     mind
    -0.69
     كومونز
    -0.68
     }}"></
    -0.67
    mind
    -0.63
     Mind
    -0.61
    WindowConstants
    -0.60
    FormTagHelper
    -0.58
     MIND
    -0.58
     ویکی‌پدیا
    -0.58
    %)$
    -0.56
    POSITIVE LOGITS
     ſame
    0.62
    PREPAR
    0.57
     mignon
    0.56
    rzej
    0.55
     corren
    0.54
     Emissions
    0.54
     héro
    0.53
     ticking
    0.53
    utsu
    0.53
    bited
    0.53
    Activations Density 0.589%

    No Known Activations