© 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. 15676
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and expressions

    oai_token-act-pair · gemini-2.0-flash

    Code and math snippets

    np_max-act-logits · 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
     Pi
    -1.43
     pi
    -1.30
     PI
    -1.26
    Pi
    -1.21
    PI
    -1.16
    pi
    -1.16
     π
    -0.98
    π
    -0.83
     Pie
    -0.70
     PIP
    -0.65
    POSITIVE LOGITS
    \
    0.71
     GenerationType
    0.63
     propOrder
    0.62
     \
    0.61
     CURIAM
    0.58
     unknownFields
    0.54
    ContentAsync
    0.54
    ANTLR
    0.53
    født
    0.53
    CppMethod
    0.52
    Activations Density 5.519%

    No Known Activations