© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3981
    Prev
    Next
    INDEX
    Explanations

    angle brackets and colons that are used in XML, code and mathematical references

    oai_token-act-pair · gemini-2.0-flash

    code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     D
    -0.48
      
    -0.47
     l
    -0.44
    uerre
    -0.43
     Qu
    -0.40
     H
    -0.40
       
    -0.40
     d
    -0.40
    <eos>
    -0.40
     C
    -0.39
    POSITIVE LOGITS
     photolibrary
    0.86
    MigrationBuilder
    0.85
     AttributeSet
    0.84
     enfans
    0.81
     StringTokenizer
    0.81
     étoit
    0.81
     CreateTagHelper
    0.80
     myſelf
    0.80
     avoient
    0.80
     feroit
    0.78
    Activations Density 12.388%

    No Known Activations