© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5536
    Prev
    Next
    INDEX
    Explanations

    quotes or spoken statements by people.

    oai_token-act-pair · gemini-2.0-flash

    said

    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
    oneofs
    -0.60
    WithMany
    -0.57
     nonatomic
    -0.56
    łaś
    -0.56
    ParallelGroup
    -0.56
    simpleType
    -0.55
    bulaire
    -0.54
     add
    -0.52
    Tikang
    -0.52
    tazione
    -0.52
    POSITIVE LOGITS
    scriptcase
    0.55
     Highland
    0.47
    достатки
    0.46
    GraphicsUnit
    0.46
    AddTagHelper
    0.46
     Wikimédia
    0.45
    saucony
    0.45
    .”
    0.44
     Stratton
    0.44
     AssemblyCompany
    0.43
    Activations Density 9.491%

    No Known Activations