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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12487
    Prev
    Next
    INDEX
    Explanations

    code-related terms and syntax, especially in PHP.

    oai_token-act-pair · gemini-2.0-flash

    array-related syntax or structures

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

    array

    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
     trainers
    -0.66
     Trainers
    -0.66
    ThemeOverlay
    -0.61
     MotionEvent
    -0.60
     '\\;'
    -0.59
     DialogResult
    -0.59
     Initialized
    -0.59
    AndEndTag
    -0.58
     Administrativna
    -0.58
     trainer
    -0.57
    POSITIVE LOGITS
     array
    0.65
    array
    0.63
    basicConfig
    0.62
     ["
    0.59
     ['
    0.57
     []
    0.54
     pleaſure
    0.52
    []
    0.52
     [$
    0.51
    []=
    0.51
    Activations Density 0.778%

    No Known Activations