© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4794
    Prev
    Next
    INDEX
    Explanations

    names and compounds that start with "Han", "Lan", "Kan", "Nan", "Iw", "Tan" with some tolerance for spelling mistakes

    oai_token-act-pair · gemini-2.0-flash

    Asian names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    sizeCache
    -1.13
    LookAnd
    -1.09
     Мексичка
    -1.04
    StructEnd
    -1.02
    migrationBuilder
    -1.02
     ModelExpression
    -0.98
    FieldBuilder
    -0.95
    findpost
    -0.94
     AssemblyCulture
    -0.94
     незавершена
    -0.94
    POSITIVE LOGITS
    ex
    0.45
    ed
    0.43
    es
    0.41
    aw
    0.41
    eri
    0.40
    u
    0.40
    cha
    0.39
    jar
    0.38
    tha
    0.38
    avis
    0.37
    Activations Density 1.209%

    No Known Activations