© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5596
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns, especially "I," alongside verbs indicating action or state of being.

    oai_token-act-pair · gemini-2.0-flash

    forum/blog posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ########.
    -0.81
     AssemblyCompany
    -0.61
    AccessorTable
    -0.59
     StringTokenizer
    -0.59
    InsertCommand
    -0.59
    ándola
    -0.57
    principalTable
    -0.57
     ComVisible
    -0.57
    GeoNames
    -0.57
    évaluateur
    -0.56
    POSITIVE LOGITS
    بوابة
    0.56
    日閲覧
    0.54
    ilh
    0.51
    Искәрмәләр
    0.49
     Hin
    0.47
    Билгалдахарш
    0.46
    wyn
    0.45
    iner
    0.43
    riv
    0.43
    marginVertical
    0.42
    Activations Density 2.543%

    No Known Activations