© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5876
    Prev
    Next
    INDEX
    Explanations

    capitalized letters and abbreviations, possibly indicating names or references

    oai_token-act-pair · gemini-2.0-flash

    capitalized letters, abbreviations

    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
    ↵↵
    -1.43
     
    -1.32
     P
    -1.20
     B
    -1.18
     E
    -1.18
     S
    -1.18
     “
    -1.18
     N
    -1.18
     T
    -1.16
    ↵
    -1.14
    POSITIVE LOGITS
     myſelf
    2.45
     itſelf
    2.30
     Monfieur
    2.28
     pleaſure
    2.23
     purpoſe
    2.20
     raiſ
    2.19
     Efq
    2.19
     himſelf
    2.17
     Majefty
    2.16
     themſelves
    2.14
    Activations Density 2.787%

    No Known Activations