© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16009
    Prev
    Next
    INDEX
    Explanations

    code snippets and or mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    Short repeated strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    tagHelperRunner
    -0.79
    DoubleQuotes
    -0.71
     nahilalakip
    -0.68
    出版年
    -0.66
    tvguidetime
    -0.63
     الحره
    -0.63
    はじめに
    -0.61
    "]]
    -0.61
    Morfologia
    -0.60
    лтамалар
    -0.59
    POSITIVE LOGITS
    Portale
    0.50
     contextLoads
    0.47
     diagon
    0.44
     grave
    0.42
     biol
    0.41
    GeneratedValue
    0.41
     heraus
    0.40
    שא
    0.40
    {#
    0.40
     Auff
    0.40
    Activations Density 7.294%

    No Known Activations