© 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. 13304
    Prev
    Next
    INDEX
    Explanations

    a variety of words, some of which seem to be non-English, with no clear pattern

    oai_token-act-pair · gemini-2.0-flash

    Ook

    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
    CodedInputStream
    -0.54
     LIRE
    -0.52
     want
    -0.51
     sclero
    -0.46
     Energies
    -0.45
    ForRow
    -0.45
     consultato
    -0.44
     sī
    -0.42
     Want
    -0.42
     AppModule
    -0.42
    POSITIVE LOGITS
     <>",
    0.76
     AssemblyCulture
    0.73
    цездатний
    0.66
     diensten
    0.64
     praktijk
    0.64
     klanten
    0.64
     veiligheid
    0.63
    ksyon
    0.63
     vertrouwen
    0.63
     TextAppearance
    0.63
    Activations Density 0.285%

    No Known Activations