© 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. 13980
    Prev
    Next
    INDEX
    Explanations

    code blocks that are sets of instructions

    oai_token-act-pair · gemini-2.0-flash

    JSON structures

    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
    bootstrapcdn
    -1.37
    AndEndTag
    -1.26
     propOrder
    -1.20
     EconPapers
    -1.20
    tagHelperRunner
    -1.20
     Roskov
    -1.20
    AddTagHelper
    -1.18
     CreateTagHelper
    -1.18
     autorytatywna
    -1.17
     gynhyrchwyd
    -1.16
    POSITIVE LOGITS
    ↵↵
    0.54
     
    0.49
    ic
    0.39
      
    0.38
    ↵
    0.37
    arr
    0.37
    1
    0.36
    N
    0.34
    R
    0.32
    D
    0.32
    Activations Density 7.167%

    No Known Activations