© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10091
    Prev
    Next
    INDEX
    Explanations

    words describing appearance and shape plus bracket symbols

    oai_token-act-pair · gemini-2.0-flash

    color

    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
     "
    -0.70
    LabelTagHelper
    -0.69
     '
    -0.69
     a
    -0.66
    ibley
    -0.66
     the
    -0.63
     der
    -0.62
     her
    -0.61
     ber
    -0.61
     ou
    -0.60
    POSITIVE LOGITS
     épu
    0.81
     écout
    0.81
     doppia
    0.81
     comigo
    0.80
     creș
    0.79
     picioare
    0.79
     noastre
    0.79
     nostru
    0.78
     héri
    0.77
     originais
    0.77
    Activations Density 2.109%

    No Known Activations