© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3775
    Prev
    Next
    INDEX
    Explanations

    code snippets in a javascript context

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    MigrationBuilder
    -0.92
    ConstraintMaker
    -0.88
    Portail
    -0.77
     للاسماء
    -0.75
    TestingModule
    -0.72
     Normdatei
    -0.69
    تفصیلات
    -0.69
     للمعارف
    -0.69
    NewUrlParser
    -0.68
     marinho
    -0.68
    POSITIVE LOGITS
     ten
    0.48
    edad
    0.46
    zoon
    0.44
     age
    0.43
     prom
    0.43
    age
    0.43
     ran
    0.43
    いき
    0.42
     lí
    0.40
     oper
    0.40
    Activations Density 20.371%

    No Known Activations