© 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. 10219
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with political entities, code and math snippets and french verbs.

    oai_token-act-pair · 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
    UnusedPrivate
    -0.77
    BindView
    -0.74
    出版年
    -0.71
    +:+
    -0.69
     Dostupné
    -0.68
     cref
    -0.67
    ardos
    -0.66
     الاطلاع
    -0.65
     مشين
    -0.65
    InjectAttribute
    -0.65
    POSITIVE LOGITS
    AsUp
    0.51
    sorter
    0.47
    zzazione
    0.45
    的確
    0.45
    ModelSerializer
    0.44
    RTGC
    0.42
    рока
    0.41
     ModelExpression
    0.40
    AutoField
    0.40
     cardiaque
    0.40
    Activations Density 12.953%

    No Known Activations