© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14715
    Prev
    Next
    INDEX
    Explanations

    various code-related elements like assignments, boolean values, and specific keywords.

    oai_token-act-pair · gemini-2.0-flash

    say false

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Efq
    -1.24
     beginnetje
    -1.20
     myſelf
    -1.13
    RenderAtEndOf
    -1.11
     disambiguazione
    -1.11
     Theſe
    -1.10
    WebVitals
    -1.09
    GEBURTSDATUM
    -1.08
    WriteBarrier
    -1.07
    DockStyle
    -1.05
    POSITIVE LOGITS
     
    0.65
    !
    0.62
     !
    0.61
     FL
    0.59
     F
    0.58
     fa
    0.58
    FL
    0.54
     f
    0.52
     ف
    0.52
     na
    0.50
    Activations Density 2.169%

    No Known Activations