© 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. 6897
    Prev
    Next
    INDEX
    Explanations

    user names or identifiers from online forums

    oai_token-act-pair · gemini-2.0-flash

    tokens with specific numerical values or indicators

    np_token-act-pair-logits · gpt-4o-mini

    internet forum discussions

    np_max-act-logits · gemini-2.0-flash
    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
    NOPQRST
    -0.81
    mybatisplus
    -0.77
    kháu
    -0.73
    cestry
    -0.70
     EconPapers
    -0.69
    #
    -0.68
    TProtocol
    -0.68
    complexContent
    -0.66
    AxisAlignment
    -0.66
     '{@
    -0.63
    POSITIVE LOGITS
     neutre
    0.53
     géneros
    0.52
     cappuccio
    0.49
    ))[
    0.46
     venuto
    0.44
     piede
    0.44
     neuve
    0.42
     ready
    0.41
    exprimer
    0.41
     sicura
    0.41
    Activations Density 3.118%

    No Known Activations