© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13053
    Prev
    Next
    INDEX
    Explanations

    a mix of function calls and study results that often include the word "acr" or the letters "SE."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Personendaten
    -0.73
    orsese
    -0.59
     ostavi
    -0.57
     gainera
    -0.57
    tagext
    -0.56
    новништво
    -0.54
    protoimpl
    -0.54
     насељу
    -0.53
     BOP
    -0.53
    发表于
    -0.51
    POSITIVE LOGITS
    tvguidetime
    0.63
    κτή
    0.56
    ReusableCell
    0.56
    ChildScrollView
    0.55
     оригинала
    0.50
    mybatisplus
    0.50
    󠁢
    0.50
    posedge
    0.50
     ffilmiau
    0.49
     CreateTagHelper
    0.49
    Activations Density 15.439%

    No Known Activations