© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12279
    Prev
    Next
    INDEX
    Explanations

    rental equipment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    चूर
    0.41
    appare
    0.39
    睉
    0.38
    raining
    0.38
    uniform
    0.37
    择
    0.37
    choose
    0.37
    maintained
    0.37
    raman
    0.36
    Imidazole
    0.36
    POSITIVE LOGITS
     rental
    1.25
     Rental
    1.20
     rentals
    1.17
     renting
    1.11
     rented
    1.10
    Rental
    1.10
     rent
    1.08
     Rent
    1.07
    rental
    1.05
    租
    1.04
    Activations Density 0.069%

    No Known Activations