© 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. 11202
    Prev
    Next
    INDEX
    Explanations

    names of people and common adjacent characters such as punctuation

    oai_token-act-pair · gemini-2.0-flash

    acknowledgements in research papers

    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
    rig
    -0.41
    álat
    -0.40
     darb
    -0.40
    стол
    -0.40
    huk
    -0.39
    ksjoner
    -0.38
     den
    -0.37
     Code
    -0.36
    Der
    -0.36
     clínico
    -0.35
    POSITIVE LOGITS
     متعلقه
    1.17
     resourceCulture
    1.01
    UrlResolution
    0.90
     EconPapers
    0.89
    Vidite
    0.88
     مرئيه
    0.85
    AndEndTag
    0.84
     HasFactory
    0.82
    ########.
    0.82
     الرياضيه
    0.82
    Activations Density 0.733%

    No Known Activations