© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212947
    Prev
    Next
    INDEX
    Explanations

    air

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     Discrete
    0.42
    ണ്ടു
    0.41
    })$.
    0.40
    玼
    0.40
    Discrete
    0.38
     discursive
    0.38
     及び
    0.37
     discre
    0.36
     Strom
    0.35
    贴
    0.34
    POSITIVE LOGITS
     Air
    0.51
    Air
    0.48
    atm
    0.44
    air
    0.41
     air
    0.39
    HON
    0.38
     vzdu
    0.37
     acoustics
    0.37
    ammed
    0.37
    Atm
    0.37
    Activations Density 0.002%

    No Known Activations