© 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. 3071
    Prev
    Next
    INDEX
    Explanations

    code-related snippets and syntax, specifically from Android XML layouts and potentially Angular templates

    oai_token-act-pair · gemini-2.0-flash

    code-related tokens

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

    Code snippets

    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
     pro
    -0.47
     to
    -0.42
    бля
    -0.41
    enty
    -0.40
     Feldman
    -0.39
    ås
    -0.38
    нти
    -0.38
     l
    -0.38
    UNCIL
    -0.38
     Forschung
    -0.38
    POSITIVE LOGITS
     متعلقه
    0.91
    onActivityResult
    0.88
     initComponents
    0.83
    gameserver
    0.83
    :✨
    0.82
    ſelves
    0.82
    posedge
    0.81
     whoſe
    0.81
    ſelf
    0.80
     Monfieur
    0.76
    Activations Density 0.708%

    No Known Activations