© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66744
    Prev
    Next
    INDEX
    Explanations

    spices and flavors

    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_46_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
     coconut
    1.73
    Coconut
    1.66
     Coconut
    1.60
    coconut
    1.55
    椰
    1.30
     cocon
    1.27
     नारियल
    1.22
    🥥
    1.09
     coco
    0.93
     Coco
    0.82
    POSITIVE LOGITS
     Amman
    0.41
    憉
    0.41
     البد
    0.40
     Algerian
    0.39
     мен
    0.39
    冊
    0.39
    పురం
    0.37
    प्‍
    0.37
     Brochure
    0.37
     roman
    0.37
    Activations Density 0.026%

    No Known Activations