© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10393
    Prev
    Next
    INDEX
    Explanations

    the word "and" along with a few adjacent words related to research and study

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    řez
    -0.46
     Simplemente
    -0.45
    :%
    -0.43
    shiro
    -0.41
     Maat
    -0.40
    postId
    -0.39
     perdere
    -0.39
    AxisAlignment
    -0.39
    ,,
    -0.38
     council
    -0.38
    POSITIVE LOGITS
    SourceChecksum
    0.82
     Paglinawan
    0.79
     AssemblyCulture
    0.77
    bootstrapcdn
    0.73
     betweenstory
    0.70
     الحره
    0.68
    RegressionTest
    0.65
    الدراسه
    0.65
    migrationBuilder
    0.64
    RunAsync
    0.63
    Activations Density 1.692%

    No Known Activations