© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12982
    Prev
    Next
    INDEX
    Explanations

    sentences about government regulations or agencies

    oai_token-act-pair · gemini-2.0-flash

    specific identifiers or labels

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     GenerationType
    -0.60
     ContentValues
    -0.59
    OrBuilder
    -0.59
     '{@
    -0.55
     oprot
    -0.55
     Majefty
    -0.54
    ExtendWith
    -0.54
    findpost
    -0.54
     PLN
    -0.54
    NameInMap
    -0.53
    POSITIVE LOGITS
     للاسماء
    0.51
    BeginContext
    0.49
     Mer
    0.49
    ReusableCell
    0.48
     mer
    0.47
    зулта
    0.47
    kita
    0.46
    Mer
    0.46
     يتيمه
    0.45
    LabelTagHelper
    0.45
    Activations Density 1.015%

    No Known Activations