© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14849
    Prev
    Next
    INDEX
    Explanations

    words that are part of technical or medical documents

    oai_token-act-pair · gemini-2.0-flash

    classification and categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     autorytatywna
    -0.61
    المناصب
    -0.61
    一種
    -0.60
    évaluateur
    -0.59
    Autoritní
    -0.56
    AsUp
    -0.55
    一种
    -0.54
    ModelAdmin
    -0.53
    protoimpl
    -0.53
    comuna
    -0.52
    POSITIVE LOGITS
    phie
    0.50
    ="@+
    0.47
    URLException
    0.47
    xlarge
    0.46
    Apro
    0.46
     endwhile
    0.45
    hdashline
    0.45
    numerusform
    0.44
    openqa
    0.43
    leben
    0.43
    Activations Density 4.128%

    No Known Activations