© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9887
    Prev
    Next
    INDEX
    Explanations

    instances of citations or references

    oai_token-act-pair · gemini-2.0-flash

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    bed
    -1.20
    by
    -1.11
    b
    -0.98
    bar
    -0.90
    bi
    -0.89
    bit
    -0.88
    ben
    -0.88
    bas
    -0.87
    ba
    -0.85
    bad
    -0.85
    POSITIVE LOGITS
     B
    0.86
     getB
    0.86
     BN
    0.81
     BU
    0.80
     b
    0.80
     Б
    0.79
     BH
    0.79
     BA
    0.79
     BCS
    0.78
     BV
    0.77
    Activations Density 3.347%

    No Known Activations