© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6386
    Prev
    Next
    INDEX
    Explanations

    conditional code statement blocks in the go programming language

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements

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

    Non-English and code

    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
    MemoryWarning
    -0.51
    PreferredItem
    -0.50
    /*!
    -0.49
     character
    -0.48
    UseVisualStyle
    -0.47
    postmedia
    -0.47
    aktery
    -0.47
    клопе
    -0.47
    ніципа
    -0.47
    StreetMap
    -0.46
    POSITIVE LOGITS
    )}_
    0.59
     craindre
    0.56
    CompleteListener
    0.55
     trajets
    0.55
     asiatique
    0.54
     Paglinawan
    0.53
     pageContext
    0.53
    numerusform
    0.53
     bienfaits
    0.52
     boire
    0.51
    Activations Density 5.062%

    No Known Activations