© 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. 3914
    Prev
    Next
    INDEX
    Explanations

    the letters "D" or "LR" occuring in a document

    oai_token-act-pair · gemini-2.0-flash

    D

    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
    StructEnd
    -0.97
    EndProject
    -0.62
     Efq
    -0.62
    complexContent
    -0.62
    #+#
    -0.61
    ANTLR
    -0.61
    RenderAtEndOf
    -0.60
    GEBURTSDATUM
    -0.59
     fieldNum
    -0.58
    providedIn
    -0.58
    POSITIVE LOGITS
    ism
    0.66
    izziness
    0.59
    жо
    0.56
    yer
    0.55
    traction
    0.54
    ЛЯ
    0.52
    esserts
    0.50
    Traceback
    0.50
    logy
    0.50
    usercontent
    0.50
    Activations Density 4.862%

    No Known Activations