© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12353
    Prev
    Next
    INDEX
    Explanations

    relative positioning in time, and also common words like "the," "is," and "was."

    oai_token-act-pair · gemini-2.0-flash

    say "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    setVerticalGroup
    -0.88
    ❋
    -0.79
    Datuak
    -0.79
    Abitanti
    -0.74
    存于互联网档案馆
    -0.73
    \{\\
    -0.73
     pinulongan
    -0.72
    帖最后由
    -0.71
     Lightboxes
    -0.71
    RTLI
    -0.71
    POSITIVE LOGITS
     the
    2.16
    the
    0.91
    The
    0.68
     The
    0.68
     THE
    0.61
    ethe
    0.60
    rethe
    0.56
    enthe
    0.52
    nthe
    0.51
    ofthe
    0.51
    Activations Density 7.651%

    No Known Activations