© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2248
    Prev
    Next
    INDEX
    Explanations

    a mixed bag of function words, verbs, and sentence fragments.

    oai_token-act-pair · gemini-2.0-flash

    Code and Documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     this
    -2.61
    this
    -2.39
    This
    -1.63
     questo
    -1.59
     этого
    -1.56
     цього
    -1.55
    THIS
    -1.52
     This
    -1.48
     này
    -1.47
     dieses
    -1.46
    POSITIVE LOGITS
     th
    0.53
     Th
    0.48
    th
    0.47
    bootstrapcdn
    0.44
    icose
    0.40
    Th
    0.40
    chnen
    0.38
     يتيمه
    0.38
    ​
    0.38
     dis
    0.37
    Activations Density 1.705%

    No Known Activations