© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 425
    Prev
    Next
    INDEX
    Explanations

    descriptions of construction projects, including the type of design and services performed

    oai_token-act-pair · gemini-2.0-flash

    construction/engineering documents

    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
     saites
    -0.57
     utafitiHapana
    -0.55
    دم
    -0.54
     jute
    -0.49
     Dise
    -0.47
     InputDecoration
    -0.47
    enedor
    -0.46
    mentation
    -0.45
    Dise
    -0.45
    pital
    -0.44
    POSITIVE LOGITS
    principalColumn
    0.57
    UnitTesting
    0.55
     DataTypes
    0.55
    StructEnd
    0.55
    Бахар
    0.53
    ValueGenerated
    0.52
     onSave
    0.50
    OGND
    0.49
    onViewCreated
    0.49
    tagHelperRunner
    0.48
    Activations Density 6.600%

    No Known Activations