© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14258
    Prev
    Next
    INDEX
    Explanations

    text about renting, landlords, and real estate

    oai_token-act-pair · gemini-2.0-flash

    rent/rental

    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
     rent
    -2.36
     rental
    -2.19
     rented
    -2.11
     renting
    -2.03
     Rent
    -2.03
     rents
    -2.02
    Rent
    -2.00
     rentals
    -1.99
     RENT
    -1.97
     Rental
    -1.95
    POSITIVE LOGITS
    PhysRevD
    0.62
    +#+#
    0.54
     AttributeSet
    0.53
    onomía
    0.52
    gway
    0.52
     Nadel
    0.50
     Serum
    0.49
    yorsunuz
    0.48
     Bourgoin
    0.48
     Wikimédia
    0.47
    Activations Density 2.458%

    No Known Activations