© 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. 9294
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate a news article or published report

    oai_token-act-pair · gemini-2.0-flash

    Formal text

    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
     Ban
    -0.59
     Kna
    -0.57
    iffance
    -0.57
     Rag
    -0.57
     Fag
    -0.56
     Blan
    -0.55
     Bon
    -0.55
     Wad
    -0.54
     Tin
    -0.54
     HUR
    -0.53
    POSITIVE LOGITS
    ViewFeatures
    0.68
    RTEX
    0.65
    WebElementEntity
    0.60
    DeleteBehavior
    0.60
    ſelf
    0.60
     ſtate
    0.59
     ſche
    0.58
     Jefus
    0.57
     Aún
    0.56
     pleaſure
    0.56
    Activations Density 1.985%

    No Known Activations