© 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. 11523
    Prev
    Next
    INDEX
    Explanations

    text related to electrical connections and cables

    oai_token-act-pair · gemini-2.0-flash

    electricity

    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
     ModelExpression
    -0.73
    issau
    -0.66
     שוליים
    -0.64
    lorette
    -0.60
    الإنجليزية
    -0.59
     nî
    -0.59
    irability
    -0.55
     Audiodateien
    -0.54
    itarian
    -0.54
    igshid
    -0.53
    POSITIVE LOGITS
    bayern
    0.44
    nowu
    0.43
    isOk
    0.43
    ździer
    0.43
    klart
    0.43
     clamps
    0.43
    Ծանոթ
    0.42
     nocturna
    0.42
     Нет
    0.42
    tett
    0.42
    Activations Density 5.064%

    No Known Activations