© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12473
    Prev
    Next
    INDEX
    Explanations

    legalese, software licenses, or copyright notices.

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     The
    -2.72
    The
    -2.27
     THE
    -1.55
    THE
    -1.54
    the
    -1.12
     the
    -0.98
    rethe
    -0.94
    sthe
    -0.90
    enthe
    -0.88
     ザ
    -0.83
    POSITIVE LOGITS
    fromnode
    0.57
    {}/
    0.54
    ORETICAL
    0.52
    ientôt
    0.51
     noqa
    0.49
    щин
    0.49
     cipolla
    0.49
    ContentLoaded
    0.49
    ldk
    0.48
    retudo
    0.47
    Activations Density 9.694%

    No Known Activations