© 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. 12802
    Prev
    Next
    INDEX
    Explanations

    statistical analyses and data in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    mathematical expressions and inequality

    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
     below
    -1.45
    below
    -1.32
     <
    -1.26
     Below
    -1.25
    <
    -1.14
    Below
    -1.13
    )<
    -1.10
    }<
    -1.09
     BELOW
    -1.06
    !<
    -1.05
    POSITIVE LOGITS
    >>
    0.60
    >
    0.58
    ">\
    0.55
    numerusform
    0.54
     >
    0.52
    CrossRef
    0.52
     >>
    0.49
     ddelweddau
    0.48
    }>
    0.47
    ≫
    0.46
    Activations Density 5.059%

    No Known Activations