© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10796
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical notation.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     uſed
    -0.84
     whoſe
    -0.82
     becauſe
    -0.81
     Efq
    -0.81
     leaſt
    -0.80
     Monfieur
    -0.80
     Jefus
    -0.79
     beſt
    -0.77
    FTFY
    -0.77
     themſelves
    -0.76
    POSITIVE LOGITS
    a
    0.67
    -
    0.60
    ic
    0.59
    F
    0.58
    J
    0.57
    an
    0.55
    ad
    0.54
    ed
    0.54
    aj
    0.54
    T
    0.53
    Activations Density 4.148%

    No Known Activations