© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 16072
    Prev
    Next
    INDEX
    Explanations

    first-person narratives of events in the past.

    oai_token-act-pair · gemini-2.0-flash

    gonna

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    !
    -0.51
    U
    -0.51
     U
    -0.48
    <eos>
    -0.46
    Rec
    -0.43
     sait
    -0.42
     Rec
    -0.41
    rosa
    -0.41
     Hard
    -0.41
     US
    -0.41
    POSITIVE LOGITS
     ProtoMessage
    1.16
    principalTable
    1.03
    mybatisplus
    1.03
    AndEndTag
    1.02
    LookAnd
    0.99
    oredCriteria
    0.98
    Vidite
    0.98
     تضيفلها
    0.96
    SharedDtor
    0.94
    GEBURTSDATUM
    0.94
    Activations Density 2.844%

    No Known Activations