© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12721
    Prev
    Next
    INDEX
    Explanations

    words or short phrases related to scientific research and reporting results

    oai_token-act-pair · gemini-2.0-flash

    suggest

    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
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.79
     antaranya
    -0.72
    MENAFN
    -0.69
    ArgsConstructor
    -0.69
    SPATH
    -0.68
    Datuak
    -0.68
     newBuilder
    -0.68
     existant
    -0.66
    antaranya
    -0.66
    IZONT
    -0.66
    POSITIVE LOGITS
    <bos>
    0.67
     treat
    0.51
     towards
    0.50
     focused
    0.47
     to
    0.47
     pretty
    0.46
     treating
    0.45
     Obrador
    0.41
     ◄
    0.41
     the
    0.41
    Activations Density 1.670%

    No Known Activations