© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12521
    Prev
    Next
    INDEX
    Explanations

    statements of author contributions or acknowledgements.

    oai_token-act-pair · gemini-2.0-flash

    phrases related to acknowledgments and gratitude

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

    acknowledgements

    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
     kaarangay
    -0.47
    oplasma
    -0.47
    gtest
    -0.45
    uatu
    -0.45
    ájá
    -0.45
    rån
    -0.44
     cytoplas
    -0.43
    ----</
    -0.43
    olingo
    -0.42
    DET
    -0.42
    POSITIVE LOGITS
    enumi
    0.97
    extAlignment
    0.69
    MemoryWarning
    0.67
    #+#
    0.60
    enumii
    0.58
    DockStyle
    0.58
     like
    0.57
    setVerticalGroup
    0.56
    providedIn
    0.55
    umbent
    0.54
    Activations Density 1.012%

    No Known Activations