© 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. 10379
    Prev
    Next
    INDEX
    Explanations

    code, logic or math like statements, and the word "diamond"

    oai_token-act-pair · gemini-2.0-flash

    code and diamonds

    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
    Bref
    -0.59
    uens
    -0.52
    ElementException
    -0.52
     թվական
    -0.52
    南浔
    -0.52
     ElementRef
    -0.51
     $=-
    -0.50
    cı
    -0.50
     kasarigan
    -0.49
    WritableDatabase
    -0.49
    POSITIVE LOGITS
    <bos>
    0.71
     виправивши
    0.69
    yntaxException
    0.68
     ©️
    0.64
     NUKAT
    0.64
      
    0.63
    protoimpl
    0.60
    ↵↵
    0.60
    s
    0.59
     
    0.58
    Activations Density 0.578%

    No Known Activations