© 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. 6827
    Prev
    Next
    INDEX
    Explanations

    code snippets that create dialog boxes in Android, and potentially other UI elements and code events

    oai_token-act-pair · gemini-2.0-flash

    archaic or stylized forms of 'self'

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

    Java/Android 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
     A
    -0.71
     I
    -0.67
     let
    -0.65
     Le
    -0.63
     [
    -0.63
     Let
    -0.63
     J
    -0.61
     per
    -0.61
    adell
    -0.60
     E
    -0.60
    POSITIVE LOGITS
    ſelf
    0.98
     Efq
    0.97
     itſelf
    0.96
     Majefty
    0.93
    ſelves
    0.92
     köln
    0.91
     Jefus
    0.91
     myſelf
    0.90
     Houſe
    0.87
     greateſt
    0.85
    Activations Density 0.977%

    No Known Activations