© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10858
    Prev
    Next
    INDEX
    Explanations

    substrings from scientific publications especially journals, conferences, and publications of scientific societies, including the name of the society

    oai_token-act-pair · gemini-2.0-flash

    Science citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     autorytatywna
    -0.79
     tartalomajánló
    -0.76
     myſelf
    -0.74
     &___
    -0.73
     itſelf
    -0.71
     Савезне
    -0.69
    VERTISEMENT
    -0.68
    AndEndTag
    -0.66
    érêt
    -0.65
    WithIOException
    -0.65
    POSITIVE LOGITS
    ponses
    0.47
     So
    0.38
    of
    0.38
     Theo
    0.35
    on
    0.35
     Nac
    0.35
     Re
    0.34
     Har
    0.34
    AsUp
    0.34
    řad
    0.34
    Activations Density 1.270%

    No Known Activations