© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1384
    Prev
    Next
    INDEX
    Explanations

    greeting and thank you

    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
    setKeepCallback
    0.38
    するために
    0.37
    ろん
    0.37
    燉
    0.37
     కామె
    0.37
    𝓀
    0.37
    过来
    0.36
    toaster
    0.36
     १५
    0.36
    业务
    0.35
    POSITIVE LOGITS
     city
    0.52
     City
    0.50
     NYC
    0.45
     CITY
    0.43
    city
    0.42
    City
    0.42
     Boston
    0.41
     市
    0.40
     شهر
    0.39
     cell
    0.38
    Activations Density 0.146%

    No Known Activations