© 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. 9445
    Prev
    Next
    INDEX
    Explanations

    HTML formatting and code snippets, including tags, buttons, and navigation elements.

    oai_token-act-pair · gemini-2.0-flash

    HTML/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_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
    PerformLayout
    -0.63
    parsedMessage
    -0.59
     alphabetical
    -0.58
     broadest
    -0.58
     shortest
    -0.58
     Gorb
    -0.56
    carnation
    -0.55
    DoubleQuotes
    -0.55
     ASR
    -0.54
     Arsen
    -0.54
    POSITIVE LOGITS
     And
    0.49
    EndGlobalSection
    0.48
    /
    0.47
    +#+#
    0.45
     It
    0.44
    "}";
    0.43
     cebola
    0.43
    as
    0.42
    findpost
    0.42
    {/
    0.42
    Activations Density 2.171%

    No Known Activations