© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9998
    Prev
    Next
    INDEX
    Explanations

    language in an advertisement trying to sell a financial product

    oai_token-act-pair · gemini-2.0-flash

    technical/form contexts

    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
    -0.55
    APORE
    -0.55
    apimachinery
    -0.50
     Familienname
    -0.50
    stub
    -0.48
    WriteBarrier
    -0.47
    RetentionPolicy
    -0.47
    abestanden
    -0.47
    Pranala
    -0.46
    ioutil
    -0.46
    POSITIVE LOGITS
    HasAnnotation
    0.60
    RTGC
    0.56
     Walkover
    0.54
    idate
    0.49
     typelib
    0.49
    ")->
    0.48
     OTP
    0.46
     Mandate
    0.46
    Thir
    0.46
    ANDER
    0.46
    Activations Density 2.507%

    No Known Activations