© 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. 2014
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on indentation and/or specific coding syntax such as 'if...else' statements or file operations, but is inconsistent.

    oai_token-act-pair · gemini-2.0-flash

    codes or unique identifiers

    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
    tagHelperRunner
    -0.46
    Subview
    -0.45
     work
    -0.38
     internal
    -0.37
    CORBA
    -0.37
    work
    -0.36
    colgroup
    -0.36
     character
    -0.34
    клопе
    -0.34
     Weh
    -0.34
    POSITIVE LOGITS
    numerusform
    0.85
    
    0.77
    SourceChecksum
    0.77
    TagMode
    0.74
     bezeichneter
    0.74
     وتسجيلات
    0.73
     مرئيه
    0.71
     Мексичка
    0.68
    følgelig
    0.68
     gewe
    0.66
    Activations Density 0.202%

    No Known Activations