© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7269
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions in LaTeX, text formatting in LaTeX, and print statements

    oai_token-act-pair · gemini-2.0-flash

    programming functions and commands

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

    code and math

    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
     to
    -0.56
     $\
    -0.42
    блиоте
    -0.41
     hào
    -0.41
     (
    -0.41
     [
    -0.41
     CYTHON
    -0.41
     >>
    -0.40
     slik
    -0.40
    ittaa
    -0.40
    POSITIVE LOGITS
     propOrder
    0.81
     myſelf
    0.81
    makeConstraints
    0.75
     الدولى
    0.75
    WriteBarrier
    0.74
    PerformLayout
    0.73
     itſelf
    0.72
     صوتيه
    0.71
     autorytatywna
    0.71
    InputBorder
    0.70
    Activations Density 0.010%

    No Known Activations