© 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. 13839
    Prev
    Next
    INDEX
    Explanations

    what looks like C code defining constants including hex values and, at times, abbreviated words

    oai_token-act-pair · gemini-2.0-flash

    code/logs

    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
     put
    -0.54
    put
    -0.53
    Put
    -0.52
     Put
    -0.51
    IRQn
    -0.49
    PUT
    -0.47
     PUT
    -0.44
    hati
    -0.44
    LogManager
    -0.44
    Putting
    -0.43
    POSITIVE LOGITS
     dk
    0.75
     dq
    0.73
     diu
    0.73
    dp
    0.69
     dap
    0.67
     dg
    0.67
    DP
    0.66
     dp
    0.65
     henvisninger
    0.65
     dn
    0.65
    Activations Density 0.381%

    No Known Activations