© 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. 11364
    Prev
    Next
    INDEX
    Explanations

    internet chat/blogs, which are conversations including acronyms, emoticons, and foreign languages

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    protoimpl
    -0.71
    Gambas
    -0.67
    ethene
    -0.63
     vandens
    -0.61
    principalTable
    -0.61
    MessageOf
    -0.60
    Année
    -0.60
     vė
    -0.60
    +#+#
    -0.60
     šal
    -0.59
    POSITIVE LOGITS
     so
    0.56
     even
    0.54
     such
    0.54
     that
    0.54
     not
    0.52
     well
    0.51
     كومونز
    0.51
     which
    0.50
     no
    0.49
     thankfully
    0.49
    Activations Density 15.940%

    No Known Activations