© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12377
    Prev
    Next
    INDEX
    Explanations

    for loops, some other keywords, and punctuation in code

    oai_token-act-pair · gemini-2.0-flash

    representations of the number zero

    np_token-act-pair-logits · gpt-4o-mini

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    windowFixed
    -0.86
    styleType
    -0.85
    bootstrapcdn
    -0.85
    +#+#
    -0.84
    Personensuche
    -0.83
    EDEFAULT
    -0.83
     للاسماء
    -0.79
     cherchés
    -0.76
    ViewFeatures
    -0.74
     linkovi
    -0.73
    POSITIVE LOGITS
    0
    0.95
    ０
    0.58
     
    0.58
    ۰
    0.43
    𝟬
    0.38
     isto
    0.38
     zero
    0.38
     isso
    0.37
    ০
    0.37
    ٠
    0.36
    Activations Density 3.847%

    No Known Activations