© 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. 5167
    Prev
    Next
    INDEX
    Explanations

    parts of code snippets or mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    state

    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
    %");
    -0.76
     Савезне
    -0.73
     treas
    -0.72
     AttributeSet
    -0.72
     Scro
    -0.69
    bootstrapcdn
    -0.68
    specialchars
    -0.68
    /');
    -0.67
     мѣ
    -0.67
    RTDA
    -0.67
    POSITIVE LOGITS
    ↵↵
    0.62
     disponibilités
    0.60
     tills
    0.59
      
    0.56
    脚注の使い方
    0.55
    ponses
    0.54
     Drapeau
    0.54
    出来
    0.53
    après
    0.53
    得到
    0.52
    Activations Density 0.382%

    No Known Activations