© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12180
    Prev
    Next
    INDEX
    Explanations

    housing descriptions with information about sizes and number of bedrooms

    oai_token-act-pair · gemini-2.0-flash

    words related to real estate or property listings

    np_token-act-pair-logits · gpt-4o-mini

    real estate and housing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AnchorStyles
    -0.70
    BuilderFactory
    -0.68
    ArgsConstructor
    -0.66
     arşivlendi
    -0.63
    
    -0.59
     hansen
    -0.58
    parsedMessage
    -0.58
    脚注の使い方
    -0.57
    efeated
    -0.56
    Autoritní
    -0.56
    POSITIVE LOGITS
     وتسجيلات
    0.58
    لينكات
    0.54
     opérés
    0.47
    gole
    0.46
    bilità
    0.45
     indisponible
    0.44
    archiviato
    0.43
    aż
    0.43
     Imp
    0.43
    LocationManager
    0.42
    Activations Density 0.514%

    No Known Activations