© 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. 11812
    Prev
    Next
    INDEX
    Explanations

    references to legal entities and/or processes, such as charities, firms, and information requests.

    oai_token-act-pair · gemini-2.0-flash

    unusual characters or formatting sequences

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

    Documents and information requests

    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
    web
    -0.46
     ayude
    -0.41
    Web
    -0.38
     fondamentali
    -0.37
     millas
    -0.37
     (
    -0.36
     linkovi
    -0.36
     mukaan
    -0.35
     Palestina
    -0.35
    hommes
    -0.34
    POSITIVE LOGITS
    __":
    0.85
    __':
    0.80
    %");
    0.77
    UnsafeEnabled
    0.76
     Wikispecies
    0.76
    __':
    0.74
    __":
    0.71
     AssemblyCulture
    0.70
     Италијани
    0.70
    Cordialement
    0.69
    Activations Density 9.992%

    No Known Activations