© 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. 10889
    Prev
    Next
    INDEX
    Explanations

    the French language, specifically words and characters used in online chat

    oai_token-act-pair · gemini-2.0-flash

    words related to system commands or placeholders

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

    French and code mix

    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
    MigrationBuilder
    -0.80
     surla
    -0.78
     Meksiku
    -0.78
     '\\;'
    -0.78
    yntaxException
    -0.77
     Италијани
    -0.77
     initComponents
    -0.76
     calendriers
    -0.75
    WireFormatLite
    -0.75
     MainAxisSize
    -0.75
    POSITIVE LOGITS
    coma
    0.46
    @
    0.42
    Past
    0.42
     @
    0.41
     vez
    0.40
    }${
    0.40
    nota
    0.40
     ad
    0.39
    empty
    0.39
    half
    0.39
    Activations Density 0.563%

    No Known Activations