© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5840
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "prop" or the word "given."

    oai_token-act-pair · gemini-2.0-flash

    prop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     AssemblyCulture
    -1.05
     تضيفلها
    -1.00
    UrlResolution
    -0.95
    Personensuche
    -0.93
    styleType
    -0.93
    دانشنامهٔ
    -0.92
    ValueStyle
    -0.88
    ⓧ
    -0.88
    ++
    -0.86
    ัติ
    -0.85
    POSITIVE LOGITS
    .
    0.75
    '
    0.63
    ↵↵
    0.60
    ;
    0.59
     pernas
    0.55
    hradun
    0.54
     bileklik
    0.52
     vectorielle
    0.52
     gelin
    0.51
     paillettes
    0.51
    Activations Density 1.705%

    No Known Activations