© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16015
    Prev
    Next
    INDEX
    Explanations

    the prefix "cons"

    oai_token-act-pair · gemini-2.0-flash

    cons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    -0.79
     
    -0.63
    <tr>
    -0.56
     either
    -0.56
     történ
    -0.54
     and
    -0.54
     The
    -0.52
    The
    -0.51
     during
    -0.51
     through
    -0.51
    POSITIVE LOGITS
    Portály
    0.98
     GenerationType
    0.93
    abestanden
    0.87
    parsedMessage
    0.87
    KommentareTeilen
    0.87
     CDT
    0.86
    /*
    0.86
    DoubleQuotes
    0.85
    ГЛА
    0.85
    OrWhiteSpace
    0.83
    Activations Density 1.458%

    No Known Activations