© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5241
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting marks, especially periods at the end of lines, and also tokens related to bylines, newspapers and film companies

    oai_token-act-pair · gemini-2.0-flash

    Period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ########.
    -0.66
    Read
    -0.60
    read
    -0.59
    Diwedd
    -0.59
    .",
    -0.58
     verwijzen
    -0.58
     read
    -0.57
    ).
    -0.57
    >`;
    -0.57
     reading
    -0.56
    POSITIVE LOGITS
     by
    0.56
     ролях
    0.54
    figsize
    0.51
     at
    0.49
    LookAnd
    0.49
     '\\;'
    0.47
     pelos
    0.47
    HasForeignKey
    0.46
    WriteTagHelper
    0.46
    ItemBackground
    0.44
    Activations Density 10.524%

    No Known Activations